Tag Archives: AMD Vega

AMD Radeon Pro VII : What You Need To Know!

AMD just launched Radeon Pro VII – their latest workstation graphics card for broadcast and engineering professionals!

Here is a quick primer on what you need to know about the AMD Radeon Pro VII, including the official tech briefing!

 

AMD Radeon Pro VII : What You Need To Know!

The new AMD Radeon Pro VII graphics card is designed for post-production teams to create 8K content, as well as engineers and data scientists working on complex models with large datasets.

Here are the Radeon Pro VII’s key features :

Leading Double Precision Performance

With up to 6.5 TFLOPS (FP64) of double precision performance for demanding engineering and scientific workloads, the Radeon Pro VII graphics card provides 5.6X the performance-per-dollar versus the NVIDIA Quadro RTX on the AMD Internal Benchmark for Altair EDEM “Screw Auger” viewset. 

High-Speed Memory

The AMD Radeon Pro VII has 16 GB of HBM2 with 1 TB/s memory bandwidth and full ECC capability, allowing it to handle large and complex models and datasets smoothly with low latency.

AMD Infinity Fabric Link

This high-bandwidth, low-latency connection allows memory sharing between two AMD Radeon Pro VII GPUs, delivering up to 5.25X PCIe 3.0 x16 bandwidth with a communication speed of up to 168 GB/s peer-to-peer between GPUs.

This allows you to increase project workload size and scale, develop more complex designs and run larger simulations to drive scientific discovery.

Remote Working

Users can access their physical workstation from virtually anywhere for unhindered productivity with the remote workstation IP built into AMD Radeon Pro Software for Enterprise driver.

PCIe Support

PCIe 4.0 delivers double the bandwidth of PCIe 3.0 to enable smooth performance for 8K, multichannel image interaction.

Frame Lock / Genlock

When paired with the AMD FirePro S400 synchronisation module, this allows for precise synchronised output for display walls, digital signage and other visual displays.

Multi-Display Support

The AMD Radeon Pro VII supports up to 6 synchronised display panels, full HDR and 8K screen resolution (single display) combined with ultra-fast encode and decode support for enhanced multi-stream workflows.

 

AMD Radeon Pro VII : Specifications

Specifications AMD Radeon Pro VII
GPU Vega 20
Transistor Count 13.2 Billion
Fabrication Process 7 nm
Die Size 331 mm²
Stream Processors 3840
Single Precision 13.1 TFLOPS
Double Precision 6.5 TFLOPS
Graphics Memory 16 GB ECC HBM2
Memory Bus Width 4096-bits
Memory Speed 1000 MHz
Memory Bandwidth 1024 GB/s
Display Ports 6 x Mini-DP 1.4
TDP 250 watts

 

AMD Radeon Pro VII : Price + Availability

The AMD Radeon VII has a launch price of US$1,899, and will be available starting mid-June 2020.

 

Recommended Reading

Go Back To > Computer | Enterprise | Home

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!


The Official AMD Radeon VII Tech Briefing + Q&A Session

AMD launched the world’s first 7nm gaming GPU – the AMD Radeon VII on 7 February 2019. In addition to greatly improving its performance efficiency, it also has twice the memory capacity and bandwidth of its predecessor, the Radeon RX Vega 64.

In this article, we will share with you the official AMD Radeon VII tech briefing, as well as the Q&A session. Find out what the new AMD Radeon VII graphics card will offer gamers, and how it stacks up against the NVIDIA GeForce RTX graphics cards!

 

The Official AMD Radeon VII Tech Briefing

AMD held this exclusive tech briefing for select members of the media. We improved it with screenshots of the relevant slides, so you will be able to follow the tech briefing.

 

The Official AMD Radeon VII Q&A Session

The AMD Radeon VII tech briefing was followed by a rather long Q&A session. Check out what was asked and answered!

[adrotate group=”1″]

 

AMD Radeon VII Specifications Compared

SpecificationsAMD Radeon VIIAMD Radeon RX Vega 64AMD Radeon RX Vega 56
GPUVega 20Vega 10Vega 10
Transistor Count13.2 Billion12.5 Billion12.5 Billion
Fabrication Process7 nm14 nm14 nm
Die Size331 mm²495 mm²495 mm²
Stream Processors384040963584
Textures Per Clock240256224
Pixels Per Clock646464
Base Clock Speed1400 MHz1247 MHz1156 MHz
Boost Clock Speed1750 MHz1546 MHz1471 MHz
Texture Fillrate336~420.GT/s319~396 GT/s259~330 GT/s
Pixel Fillrate89.6~112 GP/s79.8~98.9 GP/s74.0~94.1 GP/s
Graphics Memory16 GB HBM28 GB HBM28 GB HBM2
Graphics Memory Bus Width4096-bits2048-bits2048-bits
Graphics Memory Speed1000 MHz945 MHz800 MHz
Graphics Memory Bandwidth1024 GB/s483.8 GB/s409.6 GB/s
TDP300 W295 W210 W
Launch Prices$699$499$399

 

AMD Radeon VII Price + Availability

The AMD Radeon VII is available for sale with the launch price of US$699 SEP. It will come with three free games – Resident Evil 2, Devil May Cry 5 and The Division 2.

Next Page > AMD Radeon VII Key Features | Content Creation Performance

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Radeon VII Key Features

The AMD Radeon VII is built on the second-generation Vega microarchitecture, fabricated using the latest 7 nm process technology. It is designed to deliver high refresh rates for HDR gaming at 4K60, as well as enable content creators to work with 8K content.

7nm Process Technology

The shift from the older 14 nm to the latest 7 nm process technology allows AMD to double the amount of on-die graphics memory, while reducing the die size from 495 mm² to just 331 mm².

Using a finer process technology will also allow the AMD Radeon VII to reduce power consumption as well as heat output.

2nd Generation Vega Architecture

The AMD Radeon VII is based on the 2nd Generation Vega architecture, which is an improved version of the AMD Vega architecture, and not a completely new microarchitecture.

Basically, AMD optimised the Vega microarchitecture to increase frequencies and reduce latency. They also increased the bandwidth for ROPs to improve gaming performance. In addition, they increase the number of floating point and integer accumulators to improve compute performance.

16 GB HBM2 Memory

The AMD Radeon VII comes with 16 GB of on-die HBM2 memory, delivering 1 TB/s of memory bandwidth using a wider 4,096-bit memory interface. AMD shared this comparison to show how the extra memory will help in preventing frame time spikes.

We have to point out though that those results were obtained by testing Far Cry 5 at 4K resolution on a 2K monitor (using VSR / DSR), which greatly increases memory utilisation. The effect will be less pronounced if they were testing at 4K using a 4K monitor.

Enhanced Thermal Monitoring

Older GPU designs use a single thermal sensor to measure GPU Temperature. AMD Vega-based graphics cards use a network of multiple thermal sensors to measure the Junction Temperature instead, for these benefits :

Increased performance : Controlling based on Junction Temperature from the extensive sensing network allows each GPU to reliably maximize its performance potential, while reporting an additional temperature that is more representative of the hottest parts of the GPU. 

More dependable throttling : Extensive testing on Radeon VII shows that Junction Temperature provides a more effective control point for throttling and reliable operation of the GPU. 

More control and information:  Reporting Junction Temperature in addition to GPU Temperature provides gamers and enthusiasts with more insight into, and control over the operation of their graphics cards. 

The new AMD Radeon VII has an impressive network of 64 temperature sensors distributed across the GPU. That is TWICE the thermal sensors used in the Vega 64.

[adrotate group=”1″]

 

AMD Radeon VII Performance – Content Creation

Despite being marketed as the first 7 nm gaming graphics card, AMD focused heavily on its content creation performance, with 8K video editing in particular. That’s the usage model that will really make use of its very large 16 GB graphics memory.

In DaVinci Resolve, it was comparable to the NVIDIA GeForce RTX 2080 in performance.

In Adobe Premiere, it was slightly faster than NVIDIA GeForce RTX 2080 in 8K video editing.

Only in LuxMark, an OpenCL ray tracing benchmark did it show a significant advantage over the NVIDIA GeForce RTX 2080.

In Blender, the Radeon VII is 27% faster than the Radeon RX Vega 64. The NVIDIA GeForce RTX 2080 is not shown because the results were based on using AMD Radeon ProRender.

When it’s using the native Cycles Renderer, the Radeon VII is 2-9% faster than the GeForce RTX 2080.

Next Page > AMD Radeon VII Gaming Performance | Complete Slides

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Radeon VII Performance – Gaming

1080p Gaming

At 1080p, the AMD Radeon VII was generally slightly slower than the NVIDIA GeForce RTX 2080.

4K Gaming

The AMD Radeon VII narrowed the performance gap at 4K in many games, but in at least three games – its performance worsened, compared to the GeForce RTX 2080.

 

The Complete Set Of AMD Radeon VII Presentation Slides

Here are the complete set of slides for the AMD Radeon VII presentation.

 

Recommended Reading

[adrotate group=”2″]

Go Back To > First PageComputer Systems + Hardware | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Athlon APU with Radeon Vega Graphics Tech Report!

AMD just introduced the AMD Athlon APU with Radeon Vega Graphics. They are essentially a new low-cost family of processors based on the AMD Raven Ridge APUs launched earlier this year.

In this article, we will share with you the official AMD Athlon APU with Radeon Vega Graphics tech briefing, as well as the official slides, and other details.

 

The Official AMD Athlon APU with Radeon Vega Graphics Tech Briefing

Let’s start with the official AMD Athlon APU with Radeon Vega Graphics tech briefing by Robert Hallock, AMD Senior Technical Marketing Manager. This is an improved video that we created with larger, sharper slides and gaps removed. Enjoy!

 

AMD Athlon APU with Radeon Vega Graphics

The AMD Athlon APU with Radeon Vega Graphics is what AMD calls an Accelerated Processing Unit, because it combines a processor with a graphics processor in a single die.

In the Athlon APU’s case, it is basically a cut-down version of the AMD Raven Ridge APUs launched in February 2018. It combines a Ryzen CPU with a Radeon Vega graphics processor.

 

What Are The New AMD Athlon APU Models?

AMD officially launched only one Athlon APU on 6 September 2018 – the AMD Athlon 200GE with Radeon Vega 3 Graphics. It has two Zen processor cores that is capable of handling four simultaneous threads, with three Radeon Vega Graphics compute units.

Priced at just US$55, the Athlon 200GE has a fixed 3.2 GHz clock speed, with a 35 W TDP. It comes with a 1 MB L2 cache and a 4 MB L3 cache.

AMD also announced that the AMD Athlon 220GE and Athlon 240GE models (specifications unknown) will be released sometime in Q4 2018.

 

What Motherboards Does It Support?

The AMD Athlon APU with Radeon Vega Graphics runs on the AMD AM4 platform. So you can upgrade your existing AM4 system with the new Athlon APU (with a BIOS upgrade).

Although AMD did not explicitly mention it, the AMD Athlon APU with Radeon Vega Graphics most likely supports the faster DDR4-2933 memory, so it may pay to upgrade to a newer motherboard that supports the higher DDR4 memory speed.

[adrotate group=”1″]

 

Where Does The AMD Athlon APU Fit In?

The AMD Athlon APU with Radeon Vega Graphics is meant to be a basic processor option with basic graphics capabilities. It slots in below the AMD Ryzen 3 CPU and APU models, and competes directly against the Intel Pentium and Celeron models.

With just two Zen cores and three Vega CUs, it’s definitely not meant for serious gaming. But it will be more than powerful enough to power a family computer, or a cheap office PC.

New Page > AMD Athlon APU Performance, Price + Availability, Official Slides

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!


How Fast Is The AMD Athlon APU?

AMD pit their Athlon 200GE against the Intel Pentium G4560. A couple of differences to note :

  • The Athlon 200GE runs at 3.2 GHz, while the Pentium G4560 runs at 3.5 GHz.
  • The Athlon 200GE has 5 MB of L2 and L3 cache, while the Pentium G4560 only has a 2 MB L2 cache.
  • The Athlon 200GE runs a 35 W TDP, while the Pentium G4560 has a 54 W TDP.
  • The Athlon 200GE supports DDR4-2933 memory, while the Pentium G4560 only supports DDR4-2400 memory.

The AMD Athlon 200GE was roughly equal to the Pentium G4560 in CPU performance, but has 67% better graphics performance with a 35% lower TDP. AMD estimates that this mades the Athlon 200GE 2X more efficient than the Pentium G4560.

 

A Generational Boost From Zen

Here are more benchmark comparison (sadly with no actual numbers) comparing the Athlon 200GE against the Pentium G4560, and the previous-generation AMD A6-9500E APU. The Athlon 200GE is notably twice as fast as the A6-9500E.

 

Can You Game On The AMD Athlon APU?

Well, you can… if you are satisfied with your games running at 720p. Still, it is far better than what’s possible with the processor graphics of the Intel Pentium G4560 or the A6-9500E APU.

You can boost its gaming performance with a discrete graphics card, although it will be hobbled a little by its PCIe x8 support (instead of PCIe x16).

In this test, AMD used the NVIDIA GeForce GTX 1050. The Intel Pentium G4560 was a little faster, but requires more power.

 

AMD Athlon APU Price + Availability

The AMD Athlon 200GE is priced at US$ 55, and will be available from global retailers and system integrators starting 18 September 2018, while the Athlon 220GE and 240GE processor models are slated for launch in Q4 2018.

[adrotate group=”1″]

 

The Complete AMD Athlon APU Presentation Slides

Here is a complete set of the official AMD Athlon APU with Radeon Vega Graphics presentation slides for your perusal.

 

Recommended Reading

[adrotate group=”2″]

Go Back To > First PageComputer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!


PowerColor Radeon RX Vega 56 nano Preview

AMD revealed a great many things at their Computex 2018 press conference, but the only announced product that will actually ship with immediate effect is the Radeon RX Vega 56 nano. Let’s hear from Scott Herkelman about this new graphics card, and check out the actual Vega 56 nano card, as well as its key specifications!

 

Scoot Herkelman On The Radeon RX Vega 56 nano

Here is the segment where Scott Herkelman reveals the Radeon RX Vega 56 nano graphics card, which was created and sold by PowerColor.

Basically, the PowerColor Radeon RX Vega 56 nano is a small version of the regular Radeon RX Vega 56, designed specifically for mini-ITX systems. Other than its much smaller size, it has 6-pin + 8-pin power connectors, instead of dual 8-pin power connectors.

Everything else, from its performance characteristics and power consumption appears to be the same as a regular Radeon RX Vega 56 graphics card.

 

PowerColor Radeon RX Vega 56 nano Specifications

SpecificationsPpwerColour Radeon RX Vega 56
ModelAXRX VEGA 56 NANO 8GBHBM2
GPUAMD Vega 10
Stream Processors3584
Textures Per Clock224
Pixels Per Clock64
Base Clock Speed1156 MHz
Boost Clock Speed1471 MHz
Texture Fillrate258.9~329.5 GT/s
Pixel Fillrate74.0~94.1 GP/s
Graphics Memory8 GB HBM2
Graphics Memory Bus Width2048-bits
Graphics Memory Speed800 MHz
Graphics Memory Bandwidth409.6 GB/s
TDP210 W
PCI Express Power Connectors8-pin x 1
6-pin x 1
Display PortsDisplayPort x 3
HDMI x 1
Dimensions170 mm long
95 mm tall
38 mm thick
Retail Price$449 (card only)
$599 (with Gaming Station)
[adrotate group=”1″]

 

The PowerColor Radeon RX Vega 56 nano Up Close!

Right after the Computex 2018 press conference, we had the opportunity to check out the PowerColor Radeon RX Vega 56 nano up close. Here is a video we took of the two samples AMD provided at the end of the press conference.

Interestingly, AMD actually used one of them to power the large display for their presentation.

 

Radeon RX Vega 56 nano Price + Availability

The PowerColor Radeon RX Vega 56 nano is available from 6 June 2018 onwards, with a recommended retail price of US$ 449. This is a US$ 50 premium over the regular Radeon RX Vega 56.

PowerColour is also offering a bundle with the PowerColor Gaming Station, which they’re pricing at US$ 599. The PowerColor Gaming Station alone is priced at US$ 299, so that’s at US$ 149 discount for the bundle – a really good deal!

Go Back To > Computer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD 7nm Vega Presentation + Demo + First Look!

One of the biggest revelations at the AMD Computex 2018 press conference is how well along AMD is with their 7nm efforts. Everything appears to be chugging along as planned. AMD not only shared new details about the 7nm Vega GPU, they also showed off an actual sample!

 

The 7nm Vega Revealed!

Let’s start with this presentation on the 7nm Vega by David Wang, Senior Vice-President of Engineering at the Radeon Technologies Group. Gilbert Leung then demonstrated the performance of the 7nm Vega GPU, which has 32 GB of HBM2 memory, running Cinema4D R19 with Radeon ProRender.

Here are the key points from his presentation :

  • The AMD graphics roadmap from 2017 has not changed. The AMD Vega architecture will get a 7nm die shrink this year, before an architectural change with AMD Navi in 2019.
  • The 7nm die shrink will double power efficiency, and increase performance by 1.35X.
  • The first 7nm Vega GPU will be used in their Radeon Instinct Vega 7nm accelerator, just like how the first Vega GPUs were used in their first generation Radeon Instinct accelerators.

  • In addition to the 7nm die shrink, the Radeon Instinct Vega 7nm accelerator will feature the AMD Infinity Fabric interconnect for better multi GPU performance.
  • The Radeon Instinct Vega 7nm accelerator will also support hardware virtualisation for better security and performance in virtualised environments.

  • The Radeon Instinct Vega 7nm accelerator will come with new deep learning operations, that will not only help accelerate training and inference, but also blockchain applications.
  • The 7nm Vega GPU is sampling right now, and will launch in the second half of 2018 as the Radeon Instinct Vega 7nm accelerator.
[adrotate group=”1″]

 

First Look At 7nm Vega + 7nm EPYC!

In this video, Dr. Lisa Su shows off engineering samples of the 7nm EPYC processor (on the left), and the 7nm Vega GPU (on the right).

Go Back To > Computer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Raven Ridge Desktop APU Tech Report Rev. 3.0

At CES 2018, AMD announced the AMD Raven Ridge desktop processors – the long-awaited AMD Ryzen APUs. They are basically AMD Ryzen processors with AMD Radeon Vega graphics built-in. We can now share with you the full details and our reviews of the AMD Raven Ridge desktop APUs!

Updated @ 2018-02-13 : Added the AMD Ryzen 5 2400G and Ryzen 3 2200G review links. Updated various parts of the article.

Updated @ 2018-02-10 : Added two new sections on the new CPU package, L3 cache, PCI Express lanes, and Precision Boost 2. Also updated the section on the Single CCX Configuration.

Originally posted @ 2018-02-08

[/su_spoiler]

 

The AMD Raven Ridge Desktop APU Reviews

Here are the reviews of the new AMD Raven Ridge desktop APUs.

 

The AMD Raven Ridge Desktop APUs

Raven Ridge is AMD’s codename for their Ryzen-Vega APUs (Accelerated Processing Units). First introduced in the mobile segment as the AMD Ryzen Mobile, AMD is now introducing them to the desktop market.

The new Ryzen APUs combine an AMD Ryzen CPU, with an AMD Radeon Vega GPU, in a single die.

AMD Ryzen CPU + AMD Radeon Vega GPU = AMD Ryzen APU

Desktops APUs are not new. AMD have been making them for years, and many Intel desktop processors come with integrated graphics. But AMD is still the only manufacturer to integrate “premium CPU cores” with “premium graphics cores” to deliver gaming for the masses with :

  • 1080p HD+ gaming performance without a discrete graphics card
  • support for Radeon FreeSync, Radeon Chill, Enhanced Sync and Radeon ReLive

 

Single CCX Configuration

Unlike the Summit Ridge-based Ryzen CPUs, the AMD Raven Ridge processors use a single CCX configuration. This is a cost-saving measure with a much smaller die size, that also yield some performance benefits – reduced cache and memory latencies.

AMD analysed the performance of the 2+2 and 4+0 configuration and concluded that they are “roughly equivalent on average across 50+ games“.

 

Smaller L3 Cache

Using a single CCX configuration halves the Raven Ridge L3 cache size from 8 MB to 4 MB. To compensate, AMD increased their base and boost clock speeds, particularly in the Ryzen 5 2400G.

 

New CPU Package

The Raven Ridge APUs also introduce a revised CPU package, and a switch to the traditional non-metallic TIM (thermal interface material). These are again cost-cutting measures, albeit with a side benefit of allowing the Raven Ridge processors to officially support DDR4-2933 memory.

[adrotate group=”1″]

 

Precision Boost 2

The new Raven Ridge processors also boast the improved Precision Boost 2, whose more graceful and linear boost algorithm allows them to “boost more cores, more often, on more workloads“. It is now able to change frequencies in very fine granularity of just 25 MHz.

According to AMD, this will allow the Raven Ridge processors to perform better with apps and games that spawn many lightweight threads, as opposed to apps with persistent loads (e.g. video editing and 3D rendering).

 

PCIe x8 For Discrete GPU

The Summit Ridge-based AMD Ryzen 7, Ryzen 5 and Ryzen 3 processors have 16 PCI Express 3.0 lanes dedicated to the PCIe graphics card. In Raven Ridge, that gets cut down to half. That means any external graphics card will only communicate with a Raven Ridge processor at PCIe x8 speed.

This is a cost-saving measure, making the Raven Ridge processor simpler and cheaper to produce. The Ryzen 3 2200G, for example, is $10 cheaper than its predecessor, the Ryzen 3 1200. They also claim that the move contributed to a smaller and more efficient uncore.

AMD made this decision because “abundant public data has shown that this is a neutral change for the midrange GPUs and workloads likely to be paired with a $99-169 processor“.

Frankly, the Raven Ridge is best used as-is. If you plan to use a discrete graphics card, it makes far more sense to get the Summit Ridge-based AMD Ryzen 7, Ryzen 5 and Ryzen 3 processors instead.

Next Page > Unboxing Raven Ridge, Specifications, Price & Availability

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Ryzen 2000G Series APUs Revealed!

As announced at CES 2018, AMD is introducing two Raven Ridge desktop processors as part of the new AMD Ryzen 2000G family – the AMD Ryzen 5 2400G, and the AMD Ryzen 3 2200G.

AMD kindly sent us their Raven Ridge desktop processor media kit, which we unboxed in this video :

 

The AMD Raven Ridge Desktop APU Specification Comparison

For your convenience, we created this table that compares their key specifications with those of their CPU-equivalents – the AMD Ryzen 5 1400 and the AMD Ryzen 3 1200.

SpecificationsAMD Ryzen 5 2400GAMD Ryzen 5 1400AMD Ryzen 3 1200AMD Ryzen 3 2200G
TDP65 W65 W65 W65 W
SocketAM4AM4AM4AM4
Process Technology14 nm FinFET14 nm FinFET14 nm FinFET14 nm FinFET
Transistor Count4.94 Billion4.8 Billion4.8 Billion4.94 Billion
Die Size209.78 mm²192 mm²192 mm²209.78 mm²
CCX Configuration4+02+22+24+0
Processor Cores4444
Number of Simultaneous Threads8844
L2 Cache Size2 MB2 MB2 MB2 MB
L3 Cache Size4 MB8 MB8 MB4 MB
Base Clock Speed3.6 GHz3.2 GHz3.1 GHz3.5 GHz
Boost Clock Speed3.9 GHz3.4 GHz3.4 GHz3.7 GHz
Max. DDR4 SpeedDDR4-2933DDR4-2667DDR4-2667DDR4-2933
GPURadeon RX Vega 11
- 704 stream processors
- 44 TMUs, 16 ROPs
- Up to 1250 MHz
NoneNoneRadeon Vega 8
- 512 stream processors
- 32 TMUs, 16 ROPs
- Up to 1100 MHz
PCI Express LanesPCIe x8PCIe x16PCIe x16PCIe x8
Bundled CPU CoolerAMD Wraith StealthAMD Wraith StealthAMD Wraith StealthAMD Wraith Stealth
Launch PriceUS$ 169US$ 169US$ 109US$ 99

 

AMD Raven Ridge Price & Availability

The AMD Raven Ridge desktop APUs are available for purchase starting 12 February 2018, at the following prices :

[adrotate group=”2″]
  • AMD Ryzen 5 2400G (review) : $169 | RM 759 (inclusive of 6% GST)
  • AMD Ryzen 3 2200G (review) : $99 | RM 479 (inclusive of 6% GST)

At those price points, these Raven Ridge APUs will literally shred Intel processors with integrated graphics to pieces with their value proposition. More cores and more threads, with a much faster graphics core, at such prices. What more can you ask for?

The AMD Raven Ridge desktop APUs will be a relief to many esports gamers, who are suffering from extremely high GPU prices because of cryptocurrency miners.

 

Suggested Reading

Go Back To > First PageComputer Hardware & Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Ryzen 3 2200G With Radeon Vega 8 Graphics Review

AMD announced the AMD Ryzen 3 2200G with Radeon Vega 8 Graphics at CES 2018, and now it is finally here!. Today, we will share with you our review of the AMD Ryzen 3 2200G APU, and its integrated Radeon Vega 8 Graphics!

 

The AMD Ryzen 3 2200G Specifications Compared

We created this table to compare the specifications of the AMD Ryzen 3 2200G (Price Check) and AMD Ryzen 5 2400G (Price Check) APUs, against the AMD Ryzen 5 1400 and AMD Ryzen 3 1200 CPUs, that they will replace.

SpecificationsAMD Ryzen 5 2400GAMD Ryzen 5 1400AMD Ryzen 3 1200AMD Ryzen 3 2200G
TDP65 W65 W65 W65 W
SocketAM4AM4AM4AM4
Process Technology14 nm FinFET14 nm FinFET14 nm FinFET14 nm FinFET
Transistor Count4.94 Billion4.8 Billion4.8 Billion4.94 Billion
Die Size209.78 mm²192 mm²192 mm²209.78 mm²
CCX Configuration4+02+22+24+0
Processor Cores4444
Number of Simultaneous Threads8844
L2 Cache Size2 MB2 MB2 MB2 MB
L3 Cache Size4 MB8 MB8 MB4 MB
Base Clock Speed3.6 GHz3.2 GHz3.1 GHz3.5 GHz
Boost Clock Speed3.9 GHz3.4 GHz3.4 GHz3.7 GHz
Max. DDR4 SpeedDDR4-2933DDR4-2667DDR4-2667DDR4-2933
GPURadeon RX Vega 11
- 704 stream processors
- 44 TMUs, 16 ROPs
- Up to 1250 MHz
NoneNoneRadeon Vega 8
- 512 stream processors
- 32 TMUs, 16 ROPs
- Up to 1100 MHz
PCI Express LanesPCIe x8PCIe x16PCIe x16PCIe x8
Bundled CPU CoolerAMD Wraith StealthAMD Wraith StealthAMD Wraith StealthAMD Wraith Stealth
Launch PriceUS$ 169US$ 169US$ 109US$ 99

 

Unboxing The AMD Ryzen 5 2400G

The AMD Ryzen 3 2200G with Radeon Vega 8 Graphics (Price Check) comes bundled with an AMD Wraith Stealth cooler. Let’s unbox it, and see what we find inside!

Here is what you will find inside the box :

  • The AMD Ryzen 3 2200G APU (Price Check)
  • A pair of Ryzen and Radeon case badges
  • The AMD Wraith Stealth cooler
  • A set of AMD CPU installation guide, and motherboard compatibility note

Next Page > Key Features Of The AMD Ryzen 3 2200G

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Ryzen 3 2200G APU Up Close!

The AMD Ryzen 3 2200G with Radeon Vega 8 Graphics (Price Check) has four Ryzen processor cores with a 3.5 GHz base clock, and a 3.7 GHz boost clock. It does not support SMT (simultaneous multi-threading), so it can only handle 4 threads simultaneously.

It uses a single CCX (CPU Complex), allowing AMD to fit a Radeon GPU on the same die. Its transistor count only increased by 3% to 4.94 billion, with a 9% larger die size of 209.78 mm².

 

Single CCX Configuration

Unlike the Summit Ridge-based Ryzen CPUs, the AMD Ryzen 3 2200G (Price Check) uses a single CCX configuration. This is a cost-saving measure that yields a much smaller die size, with some performance benefits – reduced cache and memory latencies.

AMD analysed the performance of the 2+2 and 4+0 configurations, and concluded that they are “roughly equivalent on average across 50+ games“.

 

Smaller L3 Cache

Using a single CCX configuration has the unfortunate effect of halving the L3 cache size from 8 MB to 4 MB. AMD increased its base and boost clock speeds to compensate for the smaller L3 cache.

The AMD Ryzen 3 2200G has a 400 MHz (13%) higher base clock and a 300 MHz (9%) higher boost clock than the Ryzen 3 1200 it replaces.

 

New CPU Package

The Raven Ridge APUs also introduce a revised CPU package, and a switch to the traditional non-metallic TIM (thermal interface material). These are again cost-cutting measures, albeit with a side benefit of allowing the AMD Ryzen 3 2200G (Price Check) to officially support DDR4-2933 memory.

[adrotate group=”1″]

 

Precision Boost 2

The AMD Ryzen 3 2200G (Price Check) supports the improved Precision Boost 2, whose more graceful and linear boost algorithm allows them to “boost more cores, more often, on more workloads“. It can change frequencies in very fine granularity of just 25 MHz.

According to AMD, this will allow the Raven Ridge processors to perform better with apps and games that spawn many lightweight threads, as opposed to apps with persistent loads (e.g. video editing and 3D rendering).

 

PCIe x8 For Discrete GPU

The Summit Ridge-based AMD Ryzen 7, Ryzen 5 and Ryzen 3 processors have 16 PCI Express 3.0 lanes dedicated to the PCIe graphics card. The AMD Ryzen 3 2200G (Price Check) only has half that – 8 PCIe lanes. That means any external graphics card will only communicate with it at PCIe x8 speed.

This is a cost-saving measure, although AMD also claims that the move contributed to a smaller and more efficient uncore. According to AMD, this is unlikely to make a significant difference with the type of (mid-range) graphics cards this processor will usually be paired with.

 

AMD Wraith Stealth

The AMD Ryzen 3 2200G (Price Check) is bundled with the AMD Wraith Stealth cooler. This is a basic CPU cooler, so don’t expect LED or RGB lighting, a copper base or even heatpipes.

The Wraith Stealth cooler uses a simple, low-profile aluminium heatsink, with a new spring-screw clamping system. Its main advantage – it’s quiet with a maximum noise level of 28 dBa.

Next Page > 3D Rendering, Video Transcoding & Photoshop Performance

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Benchmarking The AMD Ryzen 3 2200G

In this review, we will take a look at the work and gaming performance of the AMD Ryzen 3 2200G APU. In the CPU tests, we will compare it to the AMD Ryzen 5 2400G (Price Check), as well as the AMD Ryzen 5 1500X (Price Check) and the AMD Ryzen 3 1300X (Price Check).

AMD Ryzen 5 1500X AMD Ryzen 5 2400G AMD Ryzen 3 1300X AMD Ryzen 3 2200G
Cores / Threads 4 / 8 4 / 8 4 / 4 4 / 4
Base Clock 3.5 GHz 3.6 GHz 3.5 GHz 3.5 GHz
Boost Clock 3.7 GHz 3.9 GHz 3.7 GHz 3.7 GHz
L2 Cache 2 MB 2 MB 2 MB 2 MB
L3 Cache 16 MB 4 MB 8 MB 4 MB
Memory Speed DDR4-2666 DDR4-2933 DDR4-2666 DDR4-2933
Current Price US$ 189 US$ 169 US$ 129 US$ 99

In the graphics tests, we will compare it to the NVIDIA GeForce GTX 1050 (Price Check), and the AMD Radeon RX 460 (Price Check) graphics cards. The graphics drivers used were the NVIDIA GeForce 390.77 and the AMD Radeon Software 17.7.

 

3D Rendering Speed – CINEBENCH R15

CINEBENCH R15 is a real-world 3D rendering benchmark based on the MAXON Cinema 4D animation software. This is a great way to accurately determine the actual performance of a processor in 3D content creation.

CINEBENCH R15 Single Core

This Single Core test is not reflective of real world performance, but it is useful to find out the performance of the individual core.

The AMD Ryzen 3 2200G (Price Check) has the same clock speeds as the Ryzen 3 1300X (Price Check), but was 12.4% slower in single-core performance. This shows just how much effect the larger L3 cache has on performance.

CINEBENCH R15 Multi Core

The Multi-Core test shows the processor’s real-world 3D rendering performance.

The AMD Ryzen 3 2200G (Price Check) did well in the Multi Core test, coming in only 6% slower than the Ryzen 3 1300X (Price Check), and just 24% slower than the Ryzen 5 2400G (Price Check).

CINEBENCH R15 MP Ratio

The analysis of the Multi-Processing Ratio is useful in checking the efficiency of the SMT implementation. The MP Ratio is independent of the processor’s clock speed.

It looks like the Raven Ridge microarchitecture does indeed have reduced latencies, thanks to the use of a single CCX.

[adrotate group=”1″]

 

Video Transcoding Speed – HandBrake

HandBrake is a free, open-source video transcoding utility. Video transcoding basically converts a video file from one resolution / format to another. As you can imagine, it’s very compute-intensive. In our test, we converted a 4K video of 1.3 GB in size into a 1080p video (HQ1080p30).

Despite its clock speed advantage, the AMD Ryzen 3 2200G (Price Check) was 12% slower than the Ryzen 3 1300X (Price Check) at video transcoding. This is due to the much smaller L3 cache size.

 

Radial Blur Speed – Photoshop CC 14

The radial blur filter adds the perception of motion to a picture. This is a compute-intensive operation that benefits from multiple processing cores. This radial blur test was performed on a single 13.5 megapixel photo, with a filesize of 4,910,867 bytes.

Again, the smaller L3 cache size reduced its performance by 6% compared to the Ryzen 3 1300X (Price Check).

Next Page > The 3DMark & Ashes of the Singularity Performance Results

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

3DMark – FireStrike (1920 x 1080)

In the 3DMark FireStrike benchmark that runs at 1920 x 1080, the Radeon Vega 8 core of the AMD Ryzen 3 2200G (Price Check) delivered a Graphics Score of just over 2700. This makes it less than half as fast as the AMD Radeon RX 460 (Price Check).

 

3DMark – FireStrike Extreme (2560 x 1440)

When we bumped up the resolution to 2560 x 1440, the AMD Ryzen 3 2200G delivered a Graphics Score of just 1220 – 12% slower than the Ryzen 5 2400G (Price Check).

[adrotate group=”1″]

 

Ashes of the Singularity (1080p)

In the RTS game, Ashes of the Singularity, the single core CPU performance has a significant effect on the actual frame rate. We tested the cards using the Low setting preset.

At the resolution of 1920 x 1080, the AMD Ryzen 3 2200G (Price Check) delivered a frame rate just under 25 fps. This was with the quality set to Low. So gamers will want to drop the resolution to 720p to get a decent frame rate.

 

Ashes of the Singularity (1440p)

We then bumped up the resolution to 2560 x 1440, again with the settings set to Low.

At 1440p, the average frame rate of the AMD Ryzen 3 2200G (Price Check) dropped by 12%.

Next Page > Warhammer & For Honor Performance Results

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Total War: Warhammer (1080p)

Like Ashes of the Singularity, the single core performance appears to be crucial in Total War: Warhammer.

At 1080p, the AMD Ryzen 3 2200G (Price Check) delivered a playable average frame rate of 37 fps. However, note that the quality settings were set to Low.

 

Total War: Warhammer (1440p)

We then bumped up the resolution 1440p to see how they fare, again with the quality settings set to Low.

1440p was just too hard for the Ryzen 3 2200G (Price Check) to handle. The average frame rate of 22.5 fps is just too low to be playable.

[adrotate group=”1″]

 

For Honor (1080p)

We started out testing For Honor using the Low settings, which means Trilinear Filtering and no Anti-Aliasing.

The AMD Ryzen 3 2200G (Price Check) was able to deliver a playable frame rate, which averages out at 35 fps. This makes it about ⅓ as fast as the NVIDIA GeForce GTX 1050 (Price Check) graphics card.

 

For Honor (1080p)

We then increase the resolution to 2560 x 1440, still using the Low settings.

The AMD Ryzen 3 2200G (Price Check) was definitely not powerful enough to handle the increased workload, with an average frame rate of only 21.5 fps.

Next Page > Our Verdict, Price & Availability, Suggested Reading

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Our Verdict

First off, it bears reminding that the AMD Ryzen 3 2200G (Price Check) is an APU – basically a quad-core processor, with built-in AMD Vega graphics. Even with the added graphics capability, AMD actually made the Ryzen 3 2200G cheaper than the Ryzen 3 1200 CPU it replaces.

AMD achieved this by using half of a Summit Ridge processor die, allowing 8 Vega Compute Units to be inserted with a slight bump in transistor count and die size. This clever bit of engineering compromise, and a number of other tweaks, allowed them to keep costs low.

The biggest problem with the decision to use a single CCX – the AMD Ryzen 3 2200G (Price Check) only has a 4 MB L3 cache – half that of the Ryzen 3 1200 CPU it replaces. AMD increased its clock speed to compensate, actually making the Ryzen 3 2200G equivalent to the Ryzen 3 1300X (Price Check) on paper.

As our benchmark results show, the Ryzen 3 2200G was 6-12% slower than the Ryzen 3 1300X. But that’s really okay, because the 1300X is 23% more expensive at $129!

When it comes to games, AMD promised that it will deliver “1080 HD+ gaming performance“. That may be true for less strenuous esports games like Dota 2. In the games we tested, its Radeon Vega 8 graphics core can only deliver playable frame rates at 1080p if we use the lowest possible quality settings.

[adrotate group=”2″]

Make no mistake – the Radeon Vega 8 processor graphics is no replacement for a good graphics card, like AMD’s own Radeon RX Vega 64 and Radeon RX Vega 56.

So what is the AMD Ryzen 3 2200G really good for? We see it being used mostly in small form-factor esports gaming PCs. It offers decent CPU and gaming performance for games like Dota 2, League of Legends and CS:GO in a single, highly-affordable and power-efficient package.

Remember – the AMD Ryzen 3 2200G (Price Check) offers 4-core CPU performance, with faster than average processor graphics, for just 65 watts of power consumption.

If you are looking to play games with all of the bells and whistles enabled, you need to opt for a dedicated graphics card. But if you are a casual gamer, or just want a really affordable and power-efficient esports gaming system (looking at you esports cafe owners!), it’s hard to beat the value proposition of the AMD Ryzen 3 2200G (Price Check).

Mark our words – the AMD Ryzen 3 2200G is going to shred Intel processors with integrated graphics to pieces.

 

The AMD Ryzen 3 2200G Price & Availability

As AMD announced, the AMD Ryzen 3 2200G (Price Check) desktop APU will be available starting 12 February 2018.

It is priced at just US$99 (RM 479 in Malaysia), making it an affordable gaming solution. This will be a relief to many esports gamers, who are suffering from extremely high GPU prices because of cryptocurrency miners.

You can help support Tech ARP by ordering your AMD Ryzen 3 2200G from this Amazon link.

 

Suggested Reading

Go Back To > First Page | Computer Hardware & Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD CES 2018 Updates – Ryzen APU, Ryzen PRO, Vega Mobile & More!

Las Vegas – 2018 CES – January 7, 2018 AMD (NASDAQ: AMD) today detailed its forthcoming roll-out plan for its new and next generation of high-performance computing and graphics products during the AMD CES 2018 technology update event in Las Vegas.

Alongside announcing the first desktop Ryzen processors with built-in Radeon Vega Graphics, AMD also detailed the full line-up of Ryzen Mobile APUs including the new Ryzen PRO and Ryzen 3 models, and provided a first look at the performance of its upcoming 12nm Ryzen 2 desktop CPU expected to launch in April 2018.

In graphics, AMD announced the expansion of the AMD Vega family with Radeon Vega Mobile and that its first 7nm product is planned to be a Radeon Vega GPU specifically built for machine learning applications.

 

AMD CES 2018 Technology Updates

AMD CTO and SVP Mark Papermaster shared updates on AMD’s process technology roadmaps for both x86 processors and graphics architectures.

  • x86 Processors
    • The “Zen” core, currently shipping in Ryzen desktop and mobile processors, is in production at both 14nm and 12nm, with 12nm samples now shipping.
    • The “Zen 2” design is complete and will improve on the award-winning “Zen” design in multiple dimensions.
  • Graphics Processors
    • Expanding the “Vega” product family in 2018 with the Radeon Vega Mobile GPU for ultrathin notebooks.
    • The first 7nm AMD product, a “Vega” based GPU built specifically for machine learning applications.
    • A production-level machine learning software environment with AMD’s MIOpen libraries supporting common machine learning frameworks like TensorFlow and Caffe on the ROCm Open eCosystem platform. The industry’s first fully open heterogeneous software environment, which is making it easier to program using AMD GPUs for high performance compute and deep learning environments.

 

AMD CES 2018 Client Compute Updates

AMD SVP and General Manager, Computing and Graphics Business Group, Jim Anderson detailed upcoming AMD client compute processors including:

  • The Ryzen desktop processor with Radeon graphics
    • Desktop Ryzen APUs combine the latest “Zen” core and AMD Radeon graphics engine based on the advanced “Vega” architecture, bringing:
      • The highest performance graphics engine in a desktop processor[i]
      • Advanced quad core performance with up to 8 processing threads
      • 1080p HD+ gaming performance without a discrete graphics card
      • Beautiful display features with Radeon™ FreeSync technology[ii]
      • Full benefit of Radeon software driver features including Radeon Chill, Enhanced Sync and Radeon ReLive
    • Planned to be available starting February 12, 2018.

Ryzen Desktop Processors with Radeon Vega Graphics

Model CPU Cores Threads Max Boost Clock (GHz) Graphics Compute Units[iii] Max GPU Clock (MHz) L2/L3 Cache (MB) cTDP (Watts)
Ryzen 5 2400G with Radeon RX Vega Graphics 4 8 3.9 11 1250 6 45-65W
Ryzen 3 2200G with Radeon Vega Graphics 4 4 3.7 8 1100 6 45-65W
  • 2nd generation Ryzen desktop CPU
    • AMD’s first 12nm based processor with Precision Boost 2 technology.
    • Scheduled for introduction April 2018.
  • Ryzen PRO Mobile Processors with Radeon Vega Graphics
    • Targeted for commercial, enterprise, and public sector implementation, Ryzen PRO mobile processors are designed to power sleek and powerful enterprise notebooks featuring the world’s fastest processor for commercial ultrathin notebooks[iv], state-of-the-art silicon-level security, and reliable solutions with enterprise-class support and product stack top-to-bottom DASH manageability.
      • Up to 22% more competitive productivity performance[v]
      • Up to 125% more competitive graphics performance than Intel i7-8550U and 150% more competitive graphics performance than Intel i7-7500U[vi]
      • Targeting Up to 13.5 hours of battery life[vii]
      • SenseMI[viii] features including Precision Boost 2 technology and Mobile Extended Frequency Range (mXFR)[ix]
    • Ryzen PRO mobile solutions are expected to launch in Q2 2018.

Ryzen PRO mobile processors with Radeon Vega Graphics

Model CPU Cores Threads Max Clock (GHz) Graphics Compute Units[iii] Max GPU Clock (MHz) L2/L3 Cache (MB) cTDP (Watts)
Ryzen 7 PRO 2700U with Radeon Vega Graphics 4 8 3.8 10 1300 6 15W Nominal
Ryzen 5 PRO 2500U with Radeon Vega Graphics 4 8 3.6 8 1100 6 15W Nominal
Ryzen 3 PRO 2300U with Radeon Vega Graphics 4 4 3.4 6 1100 6 15W Nominal
  • Ryzen Mobile Processor with Radeon Vega Graphics
    • AMD expanded the Ryzen Mobile Processor family, featuring the world’s fastest processor for ultrathin notebooks line up, with the introduction of the Ryzen 3 mobile processor.

Ryzen Mobile processors with Radeon Vega Graphics

Model CPU Cores Threads Max Clock (GHz) Graphics Compute Units[iii] Max GPU Clock (MHz) L2/L3 Cache (MB) cTDP (Watts)
Ryzen 7 2700U with Radeon Vega Graphics 4 8 3.8 10 1300 6 15W Nominal
Ryzen 5 2500U with Radeon Vega Graphics 4 8 3.6 8 1100 6 15W Nominal
Ryzen 3 2300U with Radeon Vega Graphics 4 4 3.4 6 1100 6 15W Nominal
Ryzen 3 2200U with Radeon Vega Graphics 2 4 3.4 3 1000 5 15W Nominal

 

AMD CES 2018 Graphics & Gaming Updates

[adrotate group=”2″]

AMD discussed its first mobile discrete graphics solution based on the “Vega” architecture. This razor-thin Radeon Vega Mobile GPU is designed to enable new, powerful gaming notebooks in 2018 with extraordinary performance and incredible efficiency.

AMD also announced that Radeon Software will add support for HDMI 2.1 Variable Refresh Rate (VRR) technology on Radeon RX products in an upcoming driver release. This support will come as an addition to the Radeon FreeSync technology umbrella, as displays with HDMI 2.1 VRR support reach market.

Ubisoft announced that Far Cry 5 will support Radeon RX Vega-specific features like Rapid Packed Math as well as Radeon FreeSync 2 technology. Radeon RX Vega owners will be able to enjoy Far Cry 5 at exceptional fidelity, with stunning frame rates and beautiful image quality.

 

AMD CES 2018 Footnotes

[i] Testing by AMD Performance labs as of 12/08/2017 for the Ryzen 5 2400G, and 09/04/2015 for the Core i7-5775c on the following systems. PC manufacturers may vary configurations yielding different results. Results may vary based on driver versions used.

System Configs: All systems equipped with Samsung 850 PRO 512GB SSD, Windows 10 RS2 operating system. Socket AM4 System: Ryzen 52400G processor, 16B (2 x 8GB) DDR4-2667 RAM, Graphics Driver 1710181048-17.40-171018a-319170E 23.20.768.0 :: 12/08/2017. Socket LGA1150 System: Core i7-5775c processor, 8GB (2x4GB) DDR3-1867 MHz RAM, graphics driver 10.18.15.4256:: 09/04/2015. 3DMark 11 Performance benchmark used to represent graphics power. The following processors achieved the following scores in 3DMark 11 ‘performance’ benchmark v1.0.132.0: The Ryzen 5 2400G: 5042. Also in v1.0.132.0, .The Core i7-5775c, the Intel desktop processor with the highest Intel desktop graphics performance, achieved 3094. RZG-01

[ii] FreeSync 2 does not require HDR capable monitors; driver can set monitor in native mode when FreeSync 2 supported HDR content is detected. Low-latency HDR only attainable when using a FreeSync 2 API enabled game or video player and content that uses at least 2x the perceivable brightness and color range of sRGB, and using a FreeSync 2 qualified monitor. Based on AMD internal testing as of November 2016. GD-105.

[iii] AMD Radeon and FirePro GPUs based on the Graphics Core Next architecture consist of multiple discrete execution engines known as a Compute Unit (“CU”). Each CU contains 64 shaders (“Stream Processors”) working together. GD-78

[iv] “Processor for ultrathin notebooks” defined as 15W nominal processor TDP. Based on testing of the AMD Ryzen 7 PRO 2700U, AMD Ryzen 5 PRO 2500U, and Core i7-8550U mobile processors as of 10/6/2017 Performance based on Cinebench R15 nT and 3DMark® TimeSpy in order of AMD Ryzen 7 PRO 2700U and Intel 8550U. Cinebench R15 nT results: 660.5, 498.2; 3DMark TimeSpy results: 978, 350. 50:50 CPU:GPU weighted relative performance with i7 baseline: Intel i7-8650U = (498.2/498.2*.5) + (350/350*.5) = 100%; AMD Ryzen 7 PRO 2700U = (660.5/498.2*.5) + (978/350*.5) = 206%.AMD Ryzen 7 PRO 2700U Processor: HP 83C6, AMD Ryzen 7 PRO 2700U Processor with Radeon Vega 10 Graphics, 8GB Dual Channel (2x4GB) DDR4-2400 RAM, Samsung 850 PRO 512GB SATA SSD, Windows 10 Pro RS2, Graphics driver 22.19.655.0, 12-Sep-2017. i7-8550U: KBL Woody_KL, i7-8550U with Intel UHD Graphics 620, 8GB Dual Channel (2x4GB) DDR4-2400 RAM, MTFDDAV256TBN – M.2 Sata, Windows 10 Pro RS2, Graphics driver 22.20.16.4771, 12-Aug-2017. Different configurations and drivers may yield different results. RPM-6

[v] Testing by AMD Performance labs. PCMark 10 Extended is used to simulate productivity performance; the AMD Ryzen 7 PRO 2700U scored 3102, while the Intel i7-8550U scored 2533 for a benchmark score comparison of 3102/2533 = 1.22X or 22% faster. AMD Ryzen™ 7 PRO 2700U: HP 83C6, AMD Ryzen™ 7 PRO 2700U with Radeon Vega 10 Processor Graphics, 8GB DDR4-2400 RAM, Samsung 850 PRO 512GB SATA SSD, Windows 10 Pro RS2, Graphics driver 22.19.655.2, 06-Sep-2017. Core i7-8550U: Acer Spin 5, Core i7-8550U with Intel UHD Graphics 620, 8GB DDR4-2400 RAM, MTFDDAV256TBN – M.2 Sata SSD, Windows 10 Pro RS2, Graphics driver 22.20.16.4771, 12-Aug-2017. Different configurations and drivers may yield different results. RPM-2

[vi] Testing by AMD Performance labs. 3DMark 11 Performance is used to simulate system performance; the AMD Ryzen 7 PRO 2700U scored 4357, while the Intel i7-8550U scored 1937 for a benchmark score comparison of 4357/1937 = 2.25X or 125% faster and the Intel i7-7500U scored 1743 for benchmark score comparison of 4357/1743 = 2.50X or 150% faster. AMD Ryzen 7 PRO 2700U: HP Envy x360 @25W, AMD Ryzen 7 PRO 2700U Processor with Radeon Vega 10 Graphics, 8GB DDR4-2400 RAM, Samsung 850 PRO 512GB SATA SSD, Windows 10 Pro RS2, Graphics driver 22.19.655.2, 06-Sep-2017. Intel Core i7-8550U: Acer Swift 3, Intel Core i7-8550U with Intel UHD Graphics 620 @15W, 16GB DDR4-2400 RAM, Samsung 850 PRO 512GB SATA SSD, Windows 10 Pro RS2, Graphics driver 22.20.16.4771, 12-Aug-2017. Intel Core i7-7500U: HP Envy x360, Intel Core i7-7500U with Intel HD Graphics 620 @15W, 8GB DDR4-2400 RAM, Samsung 850 PRO 512GB SATA SSD, Windows 10 Pro RS2, Graphics driver 22.20.16.4691 , 01-Jun-2017. Different configurations and drivers may yield different results. RPM-1

[vii] Based on AMD testing as of 10/11/2017. Battery life targets for the AMD Ryzen PRO Processor with Radeon Graphics assume a fully power-optimized software/hardware solution stack, and the following system configuration: AMD Reference Platform, AMD Ryzen 7 PRO 2700U, 2x4GB DDR4-2400, graphics driver 17.30.1025, Windows 10 x64 (1703). Assuming a 50 Wh battery capacity, MobileMark 14 battery life for the Ryzen 7 PRO 2700U playback is estimated at 13.5 hours. Different configurations and drivers may yield different results. RPM-5

[viii] AMD SenseMI technology is built into all Ryzen processors, but specific features and their enablement may vary by product and platform. mXFR enablement must meet AMD requirements. Not enabled on all notebook designs. Check with manufacturer to confirm “amplified mXFR performance” support.

[ix] mXFR enablement must meet AMD requirements. Not enabled on all notebook designs. Check with manufacturer to confirm “amplified mXFR performance” support.

Go Back To > Computer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!


Everything On The Intel CPU With Radeon Graphics! Rev. 2.0

Intel just dropped a bombshell with the announcement that they will be introducing the 8th Gen Intel CPU with Radeon graphics! This article will cover everything we can find on the upcoming 8th Gen Intel CPU with Radeon graphics, and will be updated as and when we get new information.

Updated @ 2017-11-09 : Added new information on the Chip Design, Power Saving and Performance aspects of the 8th Gen Intel CPU with Radeon graphics.

Originally posted @ 2017-11-07

 

The New Intel CPU With Radeon Graphics

The combination of an Intel CPU with Radeon graphics has long been mooted as a great way to tackle NVIDIA’s dominance of the mobile PC gaming market. Now it has finally become a reality. Here is a summary of what we know so far:

Chip Design

  • This is a multi-chip module (MCM) that combines an 8th Generation Intel Core-H mobile processor, with a customised Radeon GPU and HBM2 memory.
  • It is a mobile solution designed to deliver better gaming performance in thin and light laptops, or even smaller mobile devices (tablets?).
  • This will be the first product in the world to feature both HBM2 memory, and the Embedded Multi-Die Interconnect Bridge (EMIB).
  • As the video below shows, Intel is using the EMIB interconnect for high-bandwidth data transfers between the Radeon GPU and the HBM2 memory.
  • The distance between the CPU and the GPU is necessary to improve thermal dissipation.
  • Due to the distance between the CPU and GPU, they cannot possibly use EMIB, which can only be used for chips in close proximity. They are most likely using a regular PCI Express interconnect.

Space Saving

  • The EMIB interconnect is not only fast, it is embedded within the substrate, helping to further reduce the thickness of the package.
  • The use of stacked HBM2 memory, instead of separate GDDR5 memory chips, saves a lot of space and greatly reduces power consumption.
  • By combining the CPU, GPU and HBM2 memory on a multi-chip module, Intel claims it will save 1,900 mm² of board space.

Power Saving

  • This multi-chip module has “a unique power sharing framework” between the Intel CPU and the AMD Radeon GPU.
  • The power sharing framework is a combination of the EMIB interconnect, as well as special drivers and interfaces to the GPU.
  • The ratio of power shared between the CPU and GPU can be dynamically adjusted according to workload and usage models.
  • The power sharing framework will also help to manage temperature, power delivery and performance states in real time.
  • Intel HD Graphics will be used for less strenuous graphics functions, including video acceleration. This allows the Radeon GPU and HBM2 memory to be powered down to save power.

Performance

[adrotate group=”2″]
  • The Intel Core-H CPU used will be the 35W or 45W Kaby Lake Refresh processor, with the HD Graphics core intact.
  • Neither AMD nor Intel mentioned what Radeon GPU will be used, but their press releases emphasised that this solution is targeted at “enthusiasts” who want to play “AAA titles“.
  • This means it is most likely an AMD Vega GPU with more than 10 Compute Units, delivering better performance than the AMD Vega core in the new AMD Ryzen Mobile APUs.

Availability

  • Intel will introduce the 8th Gen Intel CPU with Radeon graphics in Q1, 2018.

Go Back To > Articles | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The World’s First AMD Ryzen Mobile Notebooks Revealed!

When AMD announced the Ryzen Mobile APUs, they also revealed the world’s first AMD Ryzen Mobile notebooks. In this article, we will share with you the specifications and key features of these notebooks. As these are preliminary details, we will update them as and when we receive new information.

 

The AMD Ryzen Mobile APU

The AMD Ryzen Mobile is not just a mobile processor, it is a mobile APU (Accelerated Processing Unit) – a combination of a traditional processor with a GPU, using a System-on-Chip design.

The new Ryzen Mobile APU combines the AMD Zen cores used in desktop Ryzen processors with AMD Vega cores used in the AMD Radeon RX Vega desktop graphics cards.

AMD announced two Ryzen Mobile models – the AMD Ryzen 7 2700U and the AMD Ryzen 5 2500U, with these specifications.

SpecificationsAMD Ryzen 7 2700UAMD Ryzen 5 2500U
CPU Cores4 Cores4 Cores
Simultaneous Threads8 Threads8 Threads
L1 Cache64 KB instruction cache
32 KB data cache
64 KB instruction cache
32 KB data cache
L2 Cache512 KB x 4512 KB x 4
L3 Cache4 MB shared4 MB shared
Base Clock Speed2.2 GHz2.0 GHz
Boost Clock Speed3.8 GHz3.6 GHz
GPU Cores10 Radeon Vega CUs8 Radeon Vega CUs
GPU ClockUp to 1.3 GHzUp to 1.1 GHz
Memory SupportUp to DDR4-2400 (Dual Channel)Up to DDR4-2400 (Dual Channel)
TDP15 W Nominal
12-25 W (Configurable)
15 W Nominal
12-25 W (Configurable)

Get more details in our article All You Need To Know About The AMD Ryzen Mobile APUs!

[adrotate group=”1″]

 

The First AMD Ryzen Mobile Notebooks

The first brands to adopt the AMD Ryzen Mobile APUs are HP, Lenovo and Acer. They are not introducing new designs though, but adapting their existing designs to fit the new Ryzen Mobile APUs. Let’s take a look at the first three Ryzen Mobile notebooks!

The HP Envy X360

The HP Envy X360 is a 15.6″ convertible laptop (we reviewed an Intel variant earlier). Earlier models are powered by either an Intel Core i7 / Core i5 processor, or an AMD FX-series processor. So it’s easy enough for HP to adapt it to the AMD Ryzen 5 2500U APU.

On top of a 1080p touch screen display, the HP Envy X360 will have dual-channel DDR4-2400 memory, and the option of either an SSD (up to 512 GB) or a 1 TB HD.

The Lenovo IdeaPad 720s

Lenovo will offer both Ryzen 7 2700U and Ryzen 5 2500U options in the Lenovo IdeaPad 720s. However, the Ryzen Mobile-powered Lenovo IdeaPad 720s will be a slightly smaller 13.3″ version of the current 14″ Intel-powered IdeaPad 720s.

The Ryzen Mobile-powered IdeaPad 720s will be 14% thinner and 26% lighter, while boasting a 1080p display. The downside – it only supports a single DDR4-2133 memory module.

The Acer Swift 3

Acer will also offer both Ryzen 7 2700U and Ryzen 5 2500U options in the upcoming Swift 3 with a 15″ full HD display.

While the display will be slightly smaller than the one in the existing Intel-powered Acer Swift 3 laptops, the Ryzen Mobile-powered model will be thinner and lighter.

[adrotate group=”1″]

 

Availability Of These Ryzen Mobile Notebooks

Neither AMD nor the three brand partners have announced the exact availability of these Ryzen Mobile laptops. AMD only announced that they will all be available in time for the holiday season. That means you should be able to purchase it in time for Christmas!

We will update this article, as and when we receive new information, so check back later!

Go Back To > Articles | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Ryzen Mobile APUs – Everything You Need To Know!

AMD has officially announced the Ryzen Mobile APUs!. Formerly codenamed Raven Ridge, they combine the AMD Zen CPU cores with AMD Vega graphics to deliver new heights in CPU and graphics performance for ultra-thin notebooks. Let’s dive into the details of the new AMD Ryzen Mobile with Radeon Vega Graphics APUs!

 

AMD Ryzen Mobile “Raven Ridge” APUs

The AMD Ryzen Mobile is not just a mobile processor, it is a mobile APU (Accelerated Processing Unit). Basically, it is a combination of a traditional processor, with a GPU, using a System-on-Chip design.

The new Ryzen Mobile APU combines the new AMD Zen cores used in desktop Ryzen processors with AMD Vega cores used in the new AMD Radeon RX Vega graphics cards.

Mobile APUs are not new. Even Intel mobile processors come with integrated graphics. But AMD is still the only manufacturer to integrate “premium CPU cores” with “premium graphics cores”.

The new CPU and GPU cores used in the new Ryzen Mobile APUs allow them to deliver 3X better CPU performance, and 2.3X better GPU performance over that of equivalent 7th Gen AMD APUs. Performance isn’t everything though. The Ryzen Mobile APUs also promise to use 58% less power!

[adrotate group=”1″]

 

The AMD Ryzen Mobile Specifications

AMD has announced two Ryzen Mobile models – the AMD Ryzen 7 2700U and the AMD Ryzen 5 2500U. Here are their specifications.

SpecificationsAMD Ryzen 7 2700UAMD Ryzen 5 2500U
CPU Cores4 Cores4 Cores
Simultaneous Threads8 Threads8 Threads
L1 Cache64 KB instruction cache
32 KB data cache
64 KB instruction cache
32 KB data cache
L2 Cache512 KB x 4512 KB x 4
L3 Cache4 MB shared4 MB shared
Base Clock Speed2.2 GHz2.0 GHz
Boost Clock Speed3.8 GHz3.6 GHz
GPU Cores10 Radeon Vega CUs8 Radeon Vega CUs
GPU ClockUp to 1.3 GHzUp to 1.1 GHz
Memory SupportUp to DDR4-2400 (Dual Channel)Up to DDR4-2400 (Dual Channel)
TDP15 W Nominal
12-25 W (Configurable)
15 W Nominal
12-25 W (Configurable)

Next Page > Precision Boost 2, Mobile XFR, Synergistic Power Rail Sharing

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Precision Boost 2

The AMD Ryzen Mobile APU introduces a new Precision Boost 2 algorithm that is part of the new AMD SenseMI technology. Instead of switching between a simple 2-core and all-core boost option, it is designed to dynamically seek the maximum possible clock speed according to the current CPU temperature, current and load.

It is also now able to change frequencies in very fine granularity of just 25 MHz. This allows for a smoother boost curve, and better boost clocks for different kinds of loads on-the-fly.

 

Mobile XFR (mXFR)

Mobile XFR (eXtended Frequency Range) is the automatic overclocking feature that boosts the processor voltage and clock speed beyond the Precision Boost clock speed. It leverages the temperature awareness of Precision Boost 2 to determine how much faster it can overclock.

Like the desktop XFR feature, it is highly dependent on the processor temperature, so a good cooling solution is necessary. Notebooks must have coolers that meet AMD’s performance criteria if they want to offer mXFR.

[adrotate group=”1″]

 

Synergistic Power Rail Sharing

The new AMD Ryzen Mobile APUs have a unified VDD power rail with digital low-dropout (LDO) regulators. This synergistic power rail sharing allows the maximum current requirements to be reduced by 36%.

They also have multiple digital LDO regions for the CPU cores, graphics core and subregions. This allows those regions to be completely turned off when they are idle, greatly saving power.

The shared voltage regulators not only reduce the total current draw, it allows the Ryzen Mobile APU to gain a higher peak CPU and GPU current to boost performance.

Next Page > Per-Core Control, Enhanced Gate States, Power Gating & Faster Gate Exit

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Per-Core Frequency & Voltage

Thanks to its fine-grained integrated voltage regulation, the AMD Ryzen Mobile APUs can dynamically adjust the frequency and voltage for each core. As each processing thread has different compute requirements, this allows the Ryzen Mobile to push power to the cores that require more performance on-the-fly.

This capability is not restricted to the CPU cores. The AMD Ryzen Mobile APUs can trade power and current between the CPU and GPU as well!

 

Enhanced Gate States

The AMD Ryzen Mobile APUs feature enhanced gate states. The CPU cores can enter CC6 power gating individually, and the L3 cache power can be lowered when all four cores are in CC6 mode. The enhanced gate states also allow the Ryzen Mobile to power down up to 95% of the Radeon Vega graphics core.

[adrotate group=”1″]

 

Dual Region Power Gating

The SoC elements of the AMD Ryzen Mobile APU are organised into two types of region. The Type A Region can remain gated during display refresh, while the Type B Region can become briefly active. This allows Type B regions to save more power during common battery life scenarios.

 

Faster Gate Exit

AMD designed the Ryzen Mobile APU to deliver 47% to 87% faster gate exits over the previous generation.

Next Page > How Fast Are The Ryzen Mobile & Radeon Vega Graphics?

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

How Fast Is The Ryzen Mobile CPU?

AMD shared the following performance results of the Ryzen Mobile CPU.

In this comparison, the AMD Ryzen 7 2700U is 8% faster than the Intel Core i7-8550U, and 10% faster than the Core i7-7500U in the single-core test.

When all four cores were enabled, the Ryzen 7 2700U was 44% faster than the Intel Core i7-8550U, and 2.2X faster than the Core i7-7500U!

Here are some additional benchmark results of the new AMD Ryzen 7 2700U and Ryzen 5 2500U APUs against the Intel Core i7-8550U and the previous-generation AMD FX-9800P APU.

 

Desktop-Class Performance

With the greatly-increased performance of the new Ryzen 7 2700U APU, AMD points out that it is slightly (7%) faster than the Intel Core i5-7600K – a quad-core desktop processor with 6X higher TDP!

[adrotate group=”1″]

 

How Fast Is Radeon Vega Graphics?

With just ten or eight Compute Units, the Radeon Vega GPU embedded into the Ryzen Mobile has nowhere near the performance of the Radeon RX Vega 64 or Vega 56 desktop graphics cards. However, they are still much faster than the mobile GPUs that both AMD and Intel have ever introduced in a mobile processor.

In the 3DMark Time Spy DirectX 12 test, the Ryzen 7 2700U with its 10 Compute Units was able to slightly beat the NVIDIA GeForce GTX 950M discrete graphics. That makes it about 2.5X faster than Intel HD Graphics.

What this means is the Radeon Vega Graphics in the AMD Ryzen 7 2700U is fast enough to deliver playable frame rates at 1080p resolution for most games.

Next Page > Battery Life, Thinner Profile, Performance Summary & Conclusion

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Better Battery Life

As pointed out earlier, AMD claims that the Ryzen Mobile APUs will deliver 58% lower power consumption, compared to the 7th Generation AMD APUs. Their benchmark results show battery life improvements from 15% to 104%.

 

Thinner Profile

The AMD Ryzen Mobile is designed for ultra-thin notebooks. The AMD Ryzen Mobile APU itself will have a 24% thinner Max Z-Height. That may not mean a lot, but when it comes to mobile devices, every millimetre counts.

 

Performance Summary

Here is a spider chart that neatly summarises the performance advantage of the AMD Ryzen 7 2700U over the Intel Core i7-8550U.

[adrotate group=”1″]

 

Conclusion

There is no doubt that the AMD Ryzen Mobile APUs are AMD’s most advanced mobile processor. This isn’t hyperbole. It’s a fact that is backed by what we have seen with their Ryzen 7, Ryzen 5 and Ryzen 3 desktop processors, as well as their Radeon RX Vega desktop graphics cards.

Finally, after many years of producing mobile APUs with lacklustre performance and high power consumption, AMD may finally have a thoroughbred in the Ryzen Mobile. We can’t wait to see the ultra-thin notebooks that will use these new APUs!

Go Back To > First Page | Computer Hardware & Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Finally Enables Radeon RX Vega CrossFire!

Ever since AMD Radeon RX Vega was launched, there have been questions about support for Radeon RX Vega CrossFire. After all, running two Radeon RX Vega cards greatly increases performance for gaming. Now the wait is over. AMD has finally enabled CrossFire for Radeon RX Vega!

 

AMD Radeon RX Vega CrossFire Is Here!

[adrotate group=”2″]

While the AMD CrossFire mode was enabled for earlier graphics cards (e.g. Radeon RX 480 CrossFire), it was not possible to use two Radeon RX Vega graphics cards in CrossFire mode. That ends with the release of Radeon Software 17.9.2.

With Radeon Software 17.9.2, you can now pair two RX Vega 56, or two RX Vega 64 graphics cards to greatly boost performance.

For some reason, AMD no longer calls this feature CrossFire, just the plain “multi GPU“. But unless they are permitting the combination of more than two graphics cards later, they should call it “dual GPU“. We think it would have been easier and better to stick with CrossFire. Every techie / gamer worth his / her salt knows what CrossFire means.

 

AMD Radeon RX Vega CrossFire Performance

Now, you may be wondering – how much of a performance boost can you expect with AMD Radeon RX Vega CrossFire?

AMD shared this slide with us. It shows the results of the benchmarks performed at the AMD Performance Lab. According to their tests, running two RX Vega 64 graphic cards in CrossFire mode (okay, multi GPU mode) delivers more than 80% faster performance in Far Cry Primal, Metro Last Night Redux, Sniper Elite 4 and The Witcher 3: Wild Hunt.

Other AMD Vega Articles

Go Back To > Computer Hardware + Systems | Home

[adrotate group=”1″]

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Radeon RX Vega 56 Review – 1440p Gaming FTW!

The road to Vega has been a rather long one. We first saw the AMD Vega prototype running DOOM in December 2016. Not unlike a baby, it took AMD nine months to give birth to the AMD Radeon RX Vega. Today, we are going to take a close look at the AMD Radeon RX Vega 56 (Price Check) graphics card that is designed to take on the NVIDIA GeForce GTX 1070. Let’s see how it performs!

 

The AMD Radeon RX Vega 56 Specification Comparison

This table compares the specifications of the AMD Radeon RX Vega 56 against those of its rival, the NVIDIA GeForce GTX 1070.

SpecificationsAMD Radeon RX Vega 64AMD Radeon RX Vega 56NVIDIA GeForce GTX 1070
GPUVega 10Vega 10NVIDIA GP104
Stream Processors409635841920
Textures Per Clock256224120
Pixels Per Clock646464
Base Clock Speed1247 MHz1156 MHz1506 MHz
Boost Clock Speed1546 MHz1471 MHz1683 MHz
Texture Fillrate319.2~395.8 GT/s258.9~329.5 GT/s180.7~202.0 GT/s
Pixel Fillrate79.8~98.9 GP/s74.0~94.1 GP/s96.4~107.7 GP/s
Graphics Memory8 GB HBM28 GB HBM28 GB GDDR5
Graphics Memory Bus Width2048-bits2048-bits256-bits
Graphics Memory Speed945 MHz800 MHz2000 MHz
Graphics Memory Bandwidth483.8 GB/s409.6 GB/s256.0 GB/s
TDP295 W210 W150 W
Retail Prices$499$399$379
$449 (Founder's Edition)

 

The AMD Radeon RX Vega 56 Up Close

The AMD Radeon RX Vega 56 (Price Check) looks exactly like the AMD Radeon RX 480, just longer. It has the same black shroud design that debuted with that Polaris-based card.

The NVIDIA GeForce GTX 1070 still offers a dual-linked DVI port, but the AMD Radeon RX Vega skips that for three DisplayPorts and a single HDMI 2.0b port.

[adrotate group=”1″]

Next Page > Power Consumption, Thermal Output, Noise Level & Benchmarking Notes

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Power Consumption

The AMD Radeon RX Vega 56 (Price Check) uses the Vega 10 GPU with 12.5 billion transistors fabricated using the 14 nm FinFET process technology. Even though it’s using a finer process technology than NVIDIA, the extra 5.3 billion transistors need more power.

Hence, the Radeon RX Vega 56 (Price Check) has a TDP of 210 W60 W (40%) more than the GeForce GTX 1070. On a watt per transistor basis, this makes the Radeon RX Vega 56 is 24% more efficient than the GeForce GTX 1070. Of course, what matters more is power efficiency on a watt / performance basis.

Curiously, AMD equipped the Radeon RX Vega 56 (Price Check) with not one, but two 8-pin PCI Express power connectors for a peak power draw of 375 W.

Incidentally, there is a GPUTach LED light strip right next to the two 8-pin PCI Express power connectors, which tells you the GPU load at a glance. There are two switches nearby that allows you to turn it on or off, and switch between the red and blue LED colours.

 

The Thermal Output

We recorded the peak exhaust temperature of the AMD Radeon RX Vega 56 (Price Check) and compared it to the GeForce GTX 1070, GeForce GTX 1060 and Radeon RX 480 graphics cards. Take a look.

Note that these are not the recorded temperatures, but how much hotter the exhaust air is above ambient temperature.

Despite its much higher TDP, the AMD Radeon RX Vega 56’s exhaust temperature is just slightly higher than that of the GeForce GTX 1070. That is likely because it uses a more powerful fan with a larger heatsink.

[adrotate group=”1″]

 

The Noise Level

Needless to say, you will be wondering about the noise level of the more powerful cooler used to keep the Radeon RX Vega 56 (Price Check) cool. In this video, we recorded the Radeon RX Vega 56 running the Ashes of the Singularity benchmark at the 4K resolution.

 

Benchmarking Notes

Our graphics benchmarking test bed has the following specifications :

Operating System : Microsoft Windows 10 64-bit

Processor : AMD Ryzen 7 1800X processor running at 3.6 GHz

Motherboard : AORUS AX370-Gaming 5

Memory : 16 GB Corsair Vengeance LPX DDR4-3000 memory (dual-channel)

Storage : 240 GB HyperX Savage SSD

Monitor : Dell P2415Q Ultra HD Monitor

We used the GeForce driver 385.41 for the NVIDIA graphics cards, and Radeon Software 17.9.1 for the AMD graphics cards.

Next Page > The AMD Radeon RX Vega 56 3DMark Benchmark Results

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

3DMark DirectX 12 Benchmark (2560 x 1440)

3DMark Time Spy is the DirectX 12 benchmark in 3DMark. It supports new API features like asynchronous compute, explicit multi-adapter, and multi-threading.

The AMD Radeon RX Vega 56 (Price Check) did well in this DirectX 12 benchmark. It was 6.5% faster than the GeForce GTX 1070, 51% faster than the GeForce GTX 1060, and 57% faster than the Radeon RX 480.

 

3DMark (1920 x 1080)

For Direct 11 performance, we started testing the graphics cards using 3DMark at the entry-level gaming resolution – 1920 x 1080.

Due to the relatively low resolution, this is a CPU-limited test for many high-end graphics cards.

The AMD Radeon RX Vega 56 (Price Check) did well in the two graphics tests, beating the GeForce GTX 1070 by 8-12%. Curiously, it ended up slower than the GeForce GTX 1070 in the combined test results.

[adrotate group=”1″]

 

3DMark (2560 x 1440)

We then took 3DMark up a notch to the resolution of 2560 x 1440. Let’s take a look at the results!

At 1440p, the AMD Radeon RX Vega 56 (Price Check) was about 10% faster in the graphics tests, and matched it in the overall score.

 

3DMark (3840 x 2160)

This is torture, even for high-end graphics cards.

At this resolution, the AMD Radeon RX Vega 56 (Price Check) did even better, beating the GeForce GTX 1070 in the graphics tests. It still tied with the GeForce GTX 1070 in the overall scores though.

Next Page > Ashes of the Singularity & Warhammer Benchmark Results

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Ashes of the Singularity (1920 x 1080)

We tested Ashes of the Singularity in the DirectX 12 mode, which supports the Asynchronous Compute feature. We started with the full HD resolution.

At this resolution, the AMD Radeon RX Vega 56 (Price Check) was 9% faster than the GeForce GTX 107028% faster than the GeForce GTX 1060, and 34% faster than the Radeon RX 480.

 

Ashes of the Singularity (2560 x 1440)

We then took Ashes of the Singularity up a notch to the resolution of 2560 x 1440. Let’s see how the cards fare now…

At this higher resolution, the performance gap between the Radeon RX Vega 56 and the GeForce GTX 1070 narrowed to 7.5%.

On the other hand, the AMD Radeon RX Vega 56 (Price Check) was now 39% faster than the GeForce GTX 1060, and 45% faster than the Radeon RX 480.

 

Ashes of the Singularity (3840 x 2160)

Finally, let’s see how the cards perform with Ashes of the Singularity running at the Ultra HD resolution of 3840 x 2160.

At this ultra high resolution, the AMD Radeon RX Vega 56 (Price Check) did well, pulling away from the GeForce GTX 1070, with an 11% performance advantage. It was also 50% faster than the GeForce GTX 1060, and 52% faster than the Radeon RX 480.

[adrotate group=”1″]

 

Warhammer (1920 x 1080)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, recorded by Total War : Warhammer‘s internal DirectX 12 benchmark.

At this resolution, most fast graphics cards are CPU-limited. Even so, the AMD Radeon RX Vega 56 (Price Check) is able to beat the GeForce GTX 1070 by 9%. Not bad.

 

Warhammer (2560 x 1440)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, recorded by Total War : Warhammer‘s internal DirectX 12 benchmark.

The 1440p resolution appears to be the sweet spot for the GeForce GTX 1070, where it almost matches the Radeon RX Vega 56 (Price Check) in performance. Both graphics cards are about 33% faster than the other three cards.

 

Warhammer (3840 x 2160)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, recorded by Total War : Warhammer‘s internal DirectX 12 benchmark.

At the Ultra HD resolution, the AMD Radeon RX Vega 56 (Price Check) widened its performance lead over the GeForce GTX 1070 to 3.4%. Both cards are now about 40% faster than the remaining three cards.

Next Page > The Witcher 3 & For Honor Benchmark Results

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The Witcher 3 (1920 x 1080)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, that FRAPS recorded in The Witcher 3.

At 1080p, the AMD Radeon RX Vega 56 (Price Check) was about 4% faster than the GeForce GTX 1070. Both graphics cards were about 40% faster than the other three cards.

 

The Witcher 3 (2560 x 1440)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, that FRAPS recorded in The Witcher 3.

At 1440p, the AMD Radeon RX Vega 56 (Price Check) maintained its 4% performance lead over the GeForce GTX 1070. Again, both graphics cards cards were about 40% faster than the remaining three cards in this comparison.

 

The Witcher 3 (3840 x 2160)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, that FRAPS recorded in The Witcher 3.

At this Ultra HD resolution, both the Radeon RX Vega 56 (Price Check) and the GeForce GTX 1070 were more or less equal in performance. They were also both about 42% faster than the remaining three cards.

[adrotate group=”1″]

 

For Honor (1920 x 1080)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, recorded by For Honor‘s internal DirectX 12 benchmark.

Both the Radeon RX Vega 56 (Price Check) and the GeForce GTX 1070 tied for the top spot, and they were both 37-46% faster than the other three cards.

 

For Honor (2560 x 1440)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, recorded by For Honor‘s internal DirectX 12 benchmark.

At the higher 1440p resolution, the NVIDIA GeForce GTX 1070 was slightly (3.2%) faster than the Radeon RX Vega 56. The AMD Radeon RX Vega 56 (Price Check) was 35% faster than the GeForce GTX 1060, and 41% faster than the Radeon RX 480.

 

For Honor (3840 x 2160)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, recorded by For Honor‘s internal DirectX 12 benchmark.

At the Ultra HD resolution, the NVIDIA GeForce GTX 1070 extended its performance lead over the Radeon RX Vega 56 to 4.4%. The AMD Radeon RX Vega 56 (Price Check) was 34% faster than the GeForce GTX 1060, and 48% faster than the Radeon RX 480.

Next Page > The Mass Effect: Andromeda Benchmark Results & Our Verdict

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Mass Effect: Andromeda (1920 x 1080)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, that FRAPS recorded in Mass Effect: Andromeda.

At this entry-level gaming resolution, all five cards did well, delivering average frame rates in excess of 60 fps. Both the Radeon RX Vega 56 (Price Check) and the GeForce GTX 1070 tied for the top spot, and they were both 24-40% faster than the other three cards.

 

Mass Effect: Andromeda (2560 x 1440)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, that FRAPS recorded in Mass Effect: Andromeda.

The NVIDIA GeForce GTX 1070 endured the jump in resolution better than the Radeon RX Vega 56 (Price Check), with a 6.7% advantage. Still, the Radeon RX Vega 56 maintain an average frame rate in excess of 60 fps, and was 28% faster than the GeForce GTX 1060, and 42% faster than the Radeon RX 480.

 

Mass Effect: Andromeda (3840 x 2160)

This chart shows you the minimum and maximum frame rates, as well as the average frame rate, that FRAPS recorded in Mass Effect: Andromeda.

The resolution increase to 4K slightly levelled the NVIDIA GeForce GTX 1070‘s performance advantage over the AMD Radeon RX Vega 56 to 6%. The AMD Radeon RX Vega 56 (Price Check) was now 33% faster than the GeForce GTX 1060, and 47% faster than the Radeon RX 480.

[adrotate group=”1″]

 

Our Verdict

Ever since we saw AMD Vega running DOOM, we had such high hopes for it. The success of the AMD Ryzen family of processors only buoyed that optimism. However, the AMD Vega turned out not to be the Pascal-killer we thought it would be.

On paper, the AMD Radeon RX Vega 56 (Price Check) has considerable advantages over the NVIDIA GeForce GTX 1070. It has a 53% advantage in texture fill rate, and a 60% advantage in memory bandwidth. The GeForce GTX 1070 only beats it in pixel fill rate by 22%.

In real life though, the AMD Radeon RX Vega 56 (Price Check) was virtually equal in performance to the NVIDIA GeForce GTX 1070. In some games, the Radeon RX Vega 56 was slightly faster. In other games, the GeForce GTX 1070 was slightly faster.

[adrotate group=”2″]

Hence, it’s no wonder AMD priced it at $399 – just $20 more than the NVIDIA GeForce GTX 1070. It would be hard to justify a higher price, especially since the GeForce GTX 1070 is already a year old!

Even though the AMD Vega GPU was built using the smaller 14 nm process technology, the AMD Radeon RX Vega 56 (Price Check) uses considerably more power because it has significantly more transistors. It has a maximum TDP of 210 W – 60 W (40%) higher than the GeForce GTX 1070.

Earlier, we pointed out that the Radeon RX Vega 56 is 24% more efficient than the GeForce GTX 1070 on a watt per transistor basis. However, the GeForce GTX 1070 is ultimately about 40% more efficient in terms of watt / performance, which is ultimately what really matters.

That said, the AMD Radeon RX Vega 56 (Price Check) is a step in the right direction. It is almost 50% faster (on average) than the Radeon RX 480, which used the last generation AMD Polaris architecture. It may not have met our overly high expectations, but it is still a big improvement.

After all, the AMD Radeon RX Vega 56 (Price Check finally offers AMD fans 1440p gaming at 60 fps at a sweet price point!

Go Back To > First PageComputer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

All You Need To Know About AMD Ryzen Threadripper! Rev. 7

AMD has finally announced the specifications, pricing and availability for the AMD Ryzen Threadripper processor! This follows their AMD Computex 2017 press conference, where they showed off the massive 16-core CPU that is targeted at the ultra-premium desktop market, directly taking on the newly-launched Intel X-Series processor.

Here is EVERYTHING you need to know about the AMD Ryzen Threadripper processors – specifications, performance, and even the special Game Mode feature! Read and SHARE!

Updated @ 2017-09-04 : We updated the availability of the Ryzen Threadripper 1900X processor, and added many links, including a link to The First AMD X399 Threadripper Motherboards. Also cleaned up many parts of the article.

Updated @ 2017-08-11 : We added the South East Asian prices, and a new page on the Ryzen Threadripper’s multithreaded CPU performance, gaming performance and the special Threadripper Game Mode option!

Updated @ 2017-07-31 : We added details of the newly-announced Ryzen Threadripper 1900X processor, and availability of all three models. We also added a new section on the Delidded Threadripper, and the secrets it revealed!

Updated @ 2017-07-26 : We added a picture of the AMD Ryzen Threadripper box!

Updated @ 2017-07-18 : We added the official AMD Ryzen Threadripper specifications and prices, confirming many of the earlier leaked details. Don’t forget to check out the official announcement video below!

Updated @ 2017-06-13 : We added new details that were just leaked about the AMD Ryzen Threadripper processor.

Originally posted @ 2017-06-05

 

The AMD Ryzen Threadripper Processor

The AMD Ryzen Threadripper will have up to 16 cores, processing up to 32 simultaneous threads. It will use the new Socket TR4, have quad-channel DDR4 memory support and feature 64 PCI Express lanes. If you were impressed by the 8-core AMD Ryzen 7 processors (read our AMD Ryzen 7 1800X review), just imagine how powerful the 16-core AMD Ryzen Threadripper processor will be.

In this video, Jim Anderson, Senior Vice-President and General Manager of the AMD Compute and Graphics business group, reveals the key features of the Threadripper CPU  and Socket TR4 platform.

Then, AMD President & CEO, Dr. Lisa Su, showed us a demo of Prey running on 4K (on Ultra High settings) using the AMD Ryzen Threadripper, with dual AMD Radeon RX Vega graphics cards. However, she did not reveal the average frame rate of this setup.

In this new video, Dr. Lisa Su and John Taylor (Corporate Vice President of Worldwide Marketing, AMD), reveal the specifications of the two first AMD Ryzen Threadripper processors (as well as the first two Ryzen 3 processors). It also shows both Ryzen Threadripper CPUs delivering higher performance in Cinebench R15 than Intel Core i9-7900X X-Series processor.

Targeted at the high-end desktop (HEDT) market, the AMD Ryzen Threadripper is paired with the X399 chipset and the new Socket TR4, offering quad memory channels and support up to 2TB of DDR4 memory, as well as 64 PCI Express 3.0 lanes!

ASRock, ASUS, GIGABYTE and MSI already have motherboards built around the AMD X399 chipset. Everything is set for the Threadripper’s epic battle against the newly-announced Intel X-Series processors!

Next Page > Specifications, Prices & Availability, The Threadripper Up Close & Delidded, Earlier Leaks

[adrotate group=”1″]

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Specifications, Prices & Availability

On 13 July 2017, AMD revealed announced the Threadripper 1950X (Lowest Price) and 1920X (Lowest Price) models. A week later, they announced the 8-core Threadripper 1900X (Lowest Price) model. Here are their specifications :

Specifications Ryzen Threadripper
1950X
Ryzen Threadripper
1920X
Ryzen Threadripper
1900X
Cores / Threads 16 / 32 12 / 24 8 / 16
Core Clock Speed 3.4 GHz 3.5 GHz 3.8 GHz
Boost Clock Speed 4.0 GHz 4.0 GHz 4.0 GHz
XFR Support Yes Yes Yes
L2 Cache Size 8 MB 6 MB 4 MB
L3 Cache Size 32 MB 32 MB 16 MB
Maximum Memory 128 GB 128 GB 128 GB
Max. TDP 180 W 180 W 180 W
Launch Price US$ 999 US$ 799 US$ 549
Availability 10 August 2017 10 August 2017 1 September 2017

Both the Ryzen Threadripper 1950X (Lowest Price) and 1920X (Lowest Price) processors are available for pre-order starting 30 July 2017, with delivery and general market availability on 10 August 2017.

AMD originally stated that the Ryzen Threadripper 1900X (Lowest Price) would be available on 31 August 2017, but they later shifted it one day later to 1 September 2017.

Here are the prices for South East Asia, with their estimated value in USD.

Countries Tax AMD Ryzen Threadripper 1950X AMD Ryzen Threadripper 1920X
United States Not inclusive USD 999 USD 799
Indonesia 10% VAT Rp 14,790,000
~USD 1,111
Rp 11,749,000
~USD 882
Malaysia 6% GST RM 4,799
~USD 1,120
RM 3,899
~USD 938
Philippines 12% VAT PHP 59,700
~USD 1,179
PHP 47,500
~USD 1,179
Singapore 7% GST SGD 1,589
~USD 1,166
SGD 1,279
~USD 938
Thailand 7% VAT ฿ 49,900
~USD 1,216
฿ 33,900
~USD 1,008
Vietnam 10% VAT 29,000,000 ₫
~USD 1,272
23,100,000 ₫
~USD 1,013

For your convenience, here are some Amazon purchase links :

  • AMD Ryzen Threadripper 1950X processor only – $999
  • AMD Ryzen Threadripper 1920X processor only – $799
  • AMD Ryzen Threadripper 1900X processor only – $549
  • AMD Ryzen Threadripper 1950X + GIGABYTE X399 AORUS Gaming 7$1389
  • AMD Ryzen Threadripper 1950X + Corsair H115i Liquid Cooler – $1124
  • AMD Ryzen Threadripper 1920X + GIGABYTE X399 AORUS Gaming 7$1189
  • AMD Ryzen Threadripper 1920X + Corsair H115i Liquid Cooler – $924

For the AMD X399 motherboard options, please take a look at Introducing The First AMD X399 Threadripper Motherboards!

 

The AMD Ryzen Threadripper Up Close

After the AMD Computex 2017 press conference, we had the opportunity to mingle with both Dr. Lisa Su and Jim Anderson. We also had the opportunity to take our first ever close-up look at the AMD Ryzen Threadripper and Ryzen Mobile CPUs. Check them out!

As you can see, this is a MASSIVE processor, with 4094 pins. It makes the AMD Ryzen Mobile APU look absolutely diminutive!

[adrotate group=”1″]

 

The AMD Ryzen Threadripper Delidded

German overclocked der8auer delidded a Threadripper processor with AMD’s permission recently, revealing many interesting facts.

  • It has four Zeppelin dies with 32 cores, but only two dies (16 cores) are functional.
  • It is functionally the AMD EPYC server processor with half the dies disabled.
  • The dies are soldered to a gold-plated heat spreader using indium solder.

Get the full nitty-gritty details in The Secrets of the Delidded Threadripper CPU Revealed!

 

Earlier Threadripper Leaks

These were the leaked information we posted earlier :

  • Although rumoured to be branded as the AMD Ryzen 9 processor (to directly compete against the newly-announced Intel Core i9 processors), AMD will be using the Ryzen Threadripper name instead. We can’t blame them – Threadripper is certainly a better and more memorable name than Ryzen 9![adrotate banner=”4″] -> Correct! AMD has announced that it will be called AMD Ryzen Threadripper!
  • AMD will launch two Threadripper processors on 27 July 2017. -> Correct!
  • The top-of-the-line processor will have 16 cores, capable of handling 32 simultaneous threads-> Correct! It is the AMD Ryzen Threadripper 1950X!
  • There will also be a 12-core processor, capable of handling 24 simultaneous threads. -> Correct! It is the AMD Ryzen Threadripper 1920X!
  • There will eventually be 14-core and 10-core versions as well.
  • All AMD Ryzen Threadripper processors will support quad DDR4 memory channels and 64 PCI Express lanes. -> Correct!
  • They are rumoured to use a solder thermal interface material (TIM), which would make deliding of the processor by enthusiasts difficult, if not impossible.  -> Correct!

Next Page > The Box, Multithreaded & Gaming Performance, Threadripper Game Mode

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Ryzen Threadripper Box

The AMD Ryzen Threadripper comes in an awesome box. Check it out!

 

Multithreaded CPU Performance

AMD shared these multithreaded performance results for the AMD Ryzen Threadripper 1950X (Lowest Price) and 1920X (Lowest Price) processors, compared to the Intel Core i9-7900X.

Here is a summary of the results, using the Intel Core i9-7900X as the baseline (100%)  :

Benchmark Intel Core i9-7900X AMD Ryzen Threadripper 1920X AMD Ryzen Threadripper 1950X
POV-Ray 3.7 100% + 6.1% + 30.8%
Adobe Premiere Pro CC 2017 100% – 4.9% + 16.7%
HandBrake 1.0.7 100% + 5.1% + 21.0%
7-Zip 16.0.2 100% + 3.5% + 26.9%
VeraCrypt 1.2.1 100% + 18.6% + 55.1%
Corona Photorealism 1.3 100% + 1.1% + 26.8%
[adrotate group=”1″]

 

1440p Gaming Performance

And here are 1440p gaming performance results on the two AMD Ryzen Threadripper processors, using the NVIDIA GeForce GTX 1080 Ti.

Here is a quick comparison of the results, using the Threadripper 1920X (Lowest Price) as the baseline (100%)  :

Benchmark AMD Ryzen Threadripper 1920X AMD Ryzen Threadripper 1950X
Rise of the Tomb Raider 100% + 0.7%
Ashes of the Singularity 100% + 5.3%
Deus Ex: Mankind Divided 100% + 2.9%
Battlefield 1 100% + 1.7%
Hitman 100% + 19.2%

 

The Threadripper Game Mode

Games are mostly optimised for quad-core processors… and rarely make use of octa-core processors. In fact, having even more cores can result in poorer performance due to poor thread scheduling. In some cases, the game may not even run at all.

To avoid those problems, AMD developer the Threadripper Game Mode. You can switch from the default “Creator Mode” to the “Game Mode” in the AMD Ryzen Master utility. Switching to Game Mode changes the Threadripper processor in two ways :

[adrotate group=”2″]
  • It temporarily disables half the CPU cores, turning the Threadripper 1950X (Lowest Price) into an 8C 16T processor like the AMD Ryzen 1800X, and the Threadripper 1920X (Lowest Price) into an 6C 12T processor like the AMD Ryzen 1600X.
  • It tells the operating system to use a Local Mode (NUMA) memory, which keeps the game and its memory footprint inside one CPU die and the locally-connected DRAM memory. This minimises several key latency points in the system, which will improve gaming performance.

Once you are done playing your game, you can switch back to Creator Mode to make full use of all of the Threadripper’s cores.

Let’s take a look at the performance difference between the Creator Mode and the Game Mode.

As you can see, the Game Mode improves the AMD Ryzen Threadripper 1950X’s gaming performance by 10% to 38%. It’s likely that disabling half the cores also allow the Threadripper to clock them higher, as there is now a much higher thermal headroom.

Go Back To > First PageArticles | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Radeon RX Vega – Everything You Need To Know!

During Computex 2017, AMD revealed that they would be formally launching the Radeon RX Vega family of GPUs in SIGGRAPH 2017. Well, it’s official – the AMD Radeon RX Vega is here! To be accurate, there are five Vega models, and they will be sold in special Radeon Packs as well. Confused? Don’t be. Let us break it down for you!

Don’t forget to also check out the following AMD Vega-related articles :

 

The Road To Vega

Several months ago, we showed off an AMD Vega prototype running DOOM on Vulkan at the 4K resolution.

During Computex 2017, Dr. Lisa Su also showed off dual AMD Vega GPUs running Prey at 4K, in an AMD Ryzen Threadripper system!

Now, they are ready for the big time! Let’s kick off with this short official introduction video from AMD!

 

The Five Vega Models

AMD announced three Radeon RX Vega models, but in reality, there are five different variants. Their names are a mouthful, but descriptive.

  • Radeon RX Vega 64 Liquid Cooled Limited Edition – 64 compute units, water-cooled, US$649
  • Radeon RX Vega 64 Liquid Cooled Edition – 64 compute units, water-cooled, US$599
  • Radeon RX Vega 64 Limited Edition – 64 compute units, US$549
  • Radeon RX Vega 64 – 64 compute units, air-cooled, US$499
  • Radeon RX Vega 56 – 56 compute units, US$399

All five cards will be available for purchase starting 14 August 2017.

[adrotate group=”1″]

 

AMD Radeon RX Vega Specifications

Models Compute Units /
Stream Processors
GPU Base Clock GPU Boost Clock Memory Type Memory Clock TDP
Radeon RX Vega 64
Liquid Cooled
Limited Edition
64 / 4096 1406 MHz 1677 MHz 2048-bit HBM2 945 MHz 345 W
Radeon RX Vega 64
Liquid Cooled Edition
64 / 4096 1406 MHz 1677 MHz 2048-bit HBM2 945 MHz 345 W
Radeon RX Vega 64
Limited Edition
64 / 4096 1247 MHz 1546 MHz 2048-bit HBM2 945 MHz 295 W
Radeon RX Vega 64 64 / 4096 1247 MHz 1546 MHz 2048-bit HBM2 945 MHz 295 W
Radeon RX Vega 56 56 / 3584 1156 MHz 1471 MHz 2048-bit HBM2 800 MHz 210 W

 

What’s With The Limited Edition?

As the specifications show, the Limited Edition cards do not offer higher clock speeds, so what’s special about them? Why pay US$50 extra for them? Here’s why…

The Limited Edition cards are AMD’s version of the NVIDIA Founders Edition graphics cards – the pinnacle of graphics card engineering. It features a solid metal shroud with a 240 grit brushed finish. Inside is a 30 mm fan mated to an isothermic vapour chamber.

There is also some bling in the form of an illuminated Vega logo in the middle of the shroud, and a Radeon pixel at the upper right corner.

Next Page > The AMD Radeon Packs, Pricing Summary

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Radeon Packs

Although you can buy the Radeon RX Vega as standalone graphics cards, AMD wants you to enjoy the complete “AMD experience”.

Introducing the AMD Radeon Packs – special bundles of a Radeon FreeSync monitor + an AMD Radeon RX Vega graphics card + an AMD Ryzen 7 CPU and motherboard combo + 2 free games!

Right now, the AMD Radeon Packs allow you to save up to US$420 off the complete package – US$200 off a 34″ Samsung CF791 curved ultrawide FreeSync monitor, US$100 off selected AMD Ryzen 7 1800X CPU and 370X motherboard combos; and two games worth US$120 (currently Wolfenstein II: The New Colossus and Prey).

The Radeon Packs will vary with region, but there will be three main Radeon Packs on offer :

  • Radeon Red Pack – with a Radeon RX Vega 56, priced at US$499.
  • Radeon Black Pack – with a Radeon RX Vega 64, priced at US$599.
  • Radeon Aqua Pack – with a Radeon RX Vega 64 Liquid Cooled Edition, priced at US$699.

Here is a closer look at the three components of an AMD Radeon Pack :

  • the 34″ Samsung CF791 curved ultrawide FreeSync monitor

  • two games worth US$120 (currently Wolfenstein II: The New Colossus and Prey).

[adrotate group=”1″]

 

AMD Radeon RX Vega Pricing Summarised

As there are many variants and Radeon Packs on offer, AMD has helpfully summarised (most of) them in this slide :

In addition to the above, there are three higher-end variants you can opt for :

  • Radeon RX Vega 64 Liquid Cooled Limited Edition – 64 compute units, water-cooled, $649
  • Radeon RX Vega 64 Liquid Cooled Edition – 64 compute units, water-cooled, $599
  • Radeon RX Vega 64 Limited Edition – 64 compute units, $549

Next Page > The Complete Set of Presentation Slides

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The Complete Set of Presentation Slides

Here is a complete set of the AMD Vega presentation slides for your perusal.

[adrotate group=”1″]

Go Back To > First Page | Computer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD Vega Memory Architecture Q&A With Jeffrey Cheng

At the AMD Computex 2017 Press Conference, AMD President & CEO Dr. Lisa Su announced that AMD will launch the Radeon Vega Frontier Edition on 27 June 2017, and the Radeon RX Vega graphics cards at the end of July 2017. We figured this is a great time to revisit the new AMD Vega memory architecture.

Now, who better to tell us all about it than AMD Senior Fellow Jeffrey Cheng, who built the AMD Vega memory architecture? Check out this exclusive Q&A session from the AMD Tech Summit in Sonoma!

Updated @ 2017-06-11 : We clarified the difference between the AMD Vega’s 64-bit flat address space, and the 512 TB addressable memory. We also added new key points, and time stamps for the key points.

Originally posted @ 2017-02-04

Don’t forget to also check out the following AMD Vega-related articles :

 

The AMD Vega Memory Architecture

Jeffrey Cheng is an AMD Senior Fellow in the area of memory architecture. The AMD Vega memory architecture refers to how the AMD Vega GPU manages memory utilisation and handles large datasets. It does not deal with the AMD Vega memory hardware design, which includes the High Bandwidth Cache and HBM2 technology.

 

AMD Vega Memory Architecture Q&A Summary

Here are the key takeaway points from the Q&A session with Jeffrey Cheng :

  • Large amounts of DRAM can be used to handle big datasets, but this is not the best solution because DRAM is costly and consumes lots of power (see 2:54).
  • AMD chose to design a heterogenous memory architecture to support various memory technologies like HBM2 and even non-volatile memory (e.g. Radeon Solid State Graphics) (see 4:40 and 8:13).[adrotate group=”2″]
  • At any given moment, the amount of data processed by the GPU is limited, so it doesn’t make sense to store a large dataset in DRAM. It would be better to cache the data required by the GPU on very fast memory (e.g. HBM2), and intelligently move them according to the GPU’s requirements (see 5:40).
  • The AMD Vega’s heterogenous memory architecture allows for easy integration of future memory technologies like storage-class memory (flash memory that can be accessed in bytes, instead of blocks) (see 8:13).
  • The AMD Vega has a 64-bit flat address space for its shaders (see 12:0812:36 and 18:21), but like NVIDIA, AMD is (very likely) limiting the addressable memory to 49-bits, giving it 512 TB of addressable memory.
  • AMD Vega has full access to the CPU’s 48-bit address space, with additional bits beyond that used to handle its own internal memory, storage and registers (see 12:16). This ties back to the High Bandwidth Cache Controller and heterogenous memory architecture, which allows the use of different memory and storage types.

  • Game developers currently try to manage data and memory usage, often extremely conservatively to support graphics cards with limited amounts of graphics memory (see 16:29).
  • With the introduction of AMD Vega, AMD wants game developers to leave data and memory management to the GPU. Its High Bandwidth Cache Controller and heterogenous memory system will automatically handle it for them (see 17:19).
  • The memory architectural advantages of AMD Vega will initially have little impact on gaming performance (due to the current conservative approach of game developers). This will change when developers hand over data and memory management to the GPU. (see 24:42).[adrotate group=”2″]
  • The improved memory architecture in AMD Vega will mainly benefit AI applications (e.g. deep machine learning) with their large datasets (see 24:52).

Don’t forget to also check out the following AMD Vega-related articles :

Go Back To > Computer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Computex 2017 Press Conference Revealed!

The most important event on Day 2 of Computex Taipei 2017 was the AMD Computex 2017 Press Conference. It was headlined by AMD President & CEO Dr. Lisa Su, and Jim Anderson, SVP and GM of the AMD Computing and Graphics division.

The hour-long press conference was, as usual, packed with information and teasers. Check out what went on during the AMD Computex 2017 press conference!

 

The AMD Computex 2017 Press Conference

The atmosphere in the room was definitely more electric this year. At Computex 2016, AMD Zen (now Ryzen) and Vega may have appeared to be pipe dreams. But at this press conference, no one doubts that AMD will deliver what they promised, and then some. It was now a matter of when, not if.

The upcoming AMD Threadripper with its 16 cores is obviously targeted at the Intel X-Series processors that were just announced yesterday. Even its chipset, the X399, seemed to be intentionally named to “beat” the Intel X299 chipset.

Meanwhile, the announcement of the AMD Ryzen Mobile processors finally injects some excitement into the mobile computing market. Not just because it will offer performance closer to that of the Intel Core processors, but also because it will be the first Ryzen APU that will feature an on-die AMD Vega GPU!

[adrotate banner=”5″]

 

Our Blow-by-Blow Account Of The AMD Computex 2017 Press Conference

This morning’s major event is the AMD Computex 2017 Press Conference

We Asians are always trying to get the front seats… with everyone else!

The AMD Computex 2017 Press Conference is about to begin!

Spencer Pan, President of AMD Greater China : 2017 is AMD’s 30th year in Taiwan.

AMD President & CEO Dr. Lisa Su kicks off the AMD Computex 2017 press conference.

Next Page > AMD EPYC, Radeon Instinct & Ryzen Mobile

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

On AMD EPYC

AMD President & CEO Dr. Lisa Su introduces AMD.

The AMD EPYC processor will deliver leadership in the 2 socket market with 45% more cores, 122% more memory bandwidth and 60% more I/O.

Here are some benchmarks of the AMD EPYC processor in 1 socket and 2 socket configurations.

AMD will launch the EPYC processor on 20 June 2017.

There you are – the AMD EPYC processor!

[adrotate banner=”5″]

AMD Radeon Instinct vs. NVIDIA Tesla P100

AMD also showed off the performance of the Vega-based Radeon Instinct against the NVIDIA Tesla P100.

 

On AMD Ryzen Mobile

Jim Anderson announces the availability of AMD Ryzen Mobile CPU.

Introducing the AMD Ryzen Mobile processor!

The AMD Ryzen Mobile processor will be the first Ryzen APU with an on-die AMD Vega GPU!

That small chip is the new AMD Ryzen Mobile processor!

Next Page > Oculus, Ryzen Threadripper, AMD Vega, Post-Event

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Oculus Approves AMD Ryzen

AMD also announced that all DESKTOP Ryzen CPUs are Oculus-approved.

 

On AMD Ryzen Threadripper

Read more about AMD Ryzen Threadripper here!

Announcing the AMD Ryzen Threadripper. AMD has officially the coolest names for their CPUs in 2017!

AMD Threadripper – 16 cores, 32 threads and 64 PCIe lanes with quad memory channels.

Ain’t she a beauty? The AMD Threadripper.

That’s as close as you’re going to get to a launch date for AMD Threadripper at this point.

Read more about AMD Ryzen Threadripper here!

[adrotate banner=”5″]

On AMD Vega

The AMD Radeon Vega Frontier Edition will launch on 27 June 2017. That’s as close as you’re going to get to a launch date for AMD Vega at this point.

Gamers will have to wait for SIGGRAPH 2017 in July. That’s when AMD will launch Radeon RX Vega!

 

Post-Event Pictures

With Dr. Lisa Su after the AMD Computex 2017 Press Conference.

With Jim Anderson and the Ryzen Threadripper after the AMD Computex 2017 Press Conference.

[adrotate banner=”5″]

Go Back To > First Page | Events | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The Computex Taipei 2017 Live Coverage (Day 2)

This is the second day of our LIVE COVERAGE of Computex Taipei 2017. You can follow us LIVE on the Tech ARP Facebook page or keep track on this article. Computex Taipei 2017 runs for five full days, and we will be here until June 2!

This article will be updated live with pictures and details as and when they come in. Videos will be inserted at the end of every night, as they take time to process and upload.

 

Day 2 Schedule

The first day of Computex 2017 is the busiest day of the event. We are scheduled for back-to-back major events from morning until evening!

9:30 AM – 11 AM : AMD Computex 2017 Press Conference

12:00 PM – 6:00 PM : ASUS, ASRock & GAMDIAS Booths… and more?

[adrotate banner=”5″]

 

AMD Computex 2017 Press Conference

Catch our full coverage and the complete video of this keynote here!

This morning’s major event is the AMD Computex 2017 Press Conference

We Asians are always trying to get the front seats… with everyone else!

The AMD Computex 2017 Press Conference is about to begin!

Spencer Pan, President of AMD Greater China : 2017 is AMD’s 30th year in Taiwan.

AMD President & CEO Dr. Lisa Su kicks off the AMD Computex 2017 press conference.

AMD President & CEO Dr. Lisa Su introduces AMD.

The AMD EPYC processor will deliver leadership in the 2 socket market with 45% more cores, 122% more memory bandwidth and 60% more I/O.

Here are some benchmarks of the AMD EPYC processor in 1 socket and 2 socket configurations.

AMD will launch the EPYC processor on 20 June 2017.

There you are – the AMD EPYC processor!

AMD also showed off the performance of the Vega-based Radeon Instinct against the NVIDIA Tesla P100.

Jim Anderson announces the availability of AMD Ryzen Mobile CPU.

Introducing the AMD Ryzen Mobile processor!

The AMD Ryzen Mobile processor will be the first Ryzen APU with an on-die AMD Vega GPU!

That small chip is the new AMD Ryzen Mobile processor!

AMD also announced that all DESKTOP Ryzen CPUs are Oculus-approved.

Announcing the AMD Threadripper. AMD has officially the coolest names for their CPUs in 2017!

AMD Threadripper – 16 cores, 32 threads and 64 PCIe lanes with quad memory channels.

Ain’t she a beauty? The AMD Threadripper.

That’s as close as you’re going to get to a launch date for AMD Threadripper at this point.

The AMD Radeon Vega Frontier Edition will launch on 27 June 2017.

That’s as close as you’re going to get to a launch date for AMD Threadripper at this point.

Gamers will have to wait for SIGGRAPH 2017 in July. That’s when AMD will launch Radeon RX Vega!

Earlier today… with Dr. Lisa Su after the AMD Computex 2017 Press Conference.

With Jim Anderson and the Ryzen Threadripper after the AMD Computex 2017 Press Conference.

Catch our full coverage and the complete video of this keynote here!

Next Page > ASUS, ASRock & GAMDIAS Booth Visits

[adrotate banner=”5″]

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

ASUS Booth Visit

Augmented reality – my two Taiwanese girlfriends, courtesy of the new ASUS ZenFone AR smartphone.

Want girlfriends like that? Get an ASUS ZenFone AR smartphone!

These ASUS ROG gaming mice are so pretty…#SoPretty

The dream gaming notebook for gamers – the new ASUS ROG Zephyrus!

 

 

 

[adrotate banner=”5″]

 

ASRock Booth Visit

Up next – ASRock. So ke ai… right?

ASRock is not a modelling agency. We reviewed their motherboards earlier… remember?

Anyway, here’s a peek at their new Intel X299 motherboards.

The ASRock team.

 

[adrotate banner=”5″]

 

 

GAMDIAS Booth Visit

Our first stop at Nangang today is GAMDIAS!

I think GAMDIAS means beauty…

This year, GAMDIAS adds gaming chairs to their range.

GAMDIAS also extended their mechanical keyboard range with a new optical key switch range!

Next Page > The Computex 2017 Live Coverage (Day 3)

[adrotate banner=”5″]

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

AMD GDC Capsaicin – Vega, Bethesda & Forward Rendering!

1 March 2017 – AMD held its GDC Capsaicin livestream event, a celebration of PC gaming, the technology steering its future, and the developers who work tirelessly to transform their imaginations into tomorrow’s blockbuster games.

 

What’s New @ AMD GDC Capsaicin

The one-hour AMD GDC Capsaicin live event offered PC gaming enthusiasts and developers around the world a preview of AMD’s latest graphics and processor technologies, revealed exciting new details surrounding Vega, and showcased the summer’s most anticipated PC and VR games from visionary game developers.

AMD and Bethesda Softworks Partner to Propel PC Gaming Forward

  • AMD and Bethesda have announced a long-term, multi-title partnership to rapidly advance game technology development, fuel new PC game experiences, and reshape the gaming landscape.
  • This brings together two titans of the gaming industry: Bethesda Softworks, which has sold more than 80 million copies of legendary games series like FalloutDOOM and Dishonored, and AMD, whose CPU and GPU technologies power the experiences of 400 million gamers worldwide.
  • The two companies will work together to develop and accelerate the implementation of new technologies, including:
    • Harnessing the full potential of low-level APIs such as Vulkan
    • Maximizing the capabilities of the computing and graphics power of AMD’s multicore AMD Ryzen CPUs, Radeon GPUs and AMD server solutions across Bethesda’s existing Bethesda franchises

AMD’s Vega GPU to Power LiquidSky Platform

  • AMD announced that its upcoming Vega architecture-based GPUs have been selected to power LiquidSky, enabling gamers around the world to enjoy the extraordinary power of Vega from anywhere.
  • LiquidSky already lets their 1.4 million beta users play any PC video game as it was meant to be enjoyed on Android phone or tablet, low-spec Windows, Mac, and even Linux devices.
  • With Vega’s powerful Radeon Virtualized Encode feature, subscribers will relish a high-quality gaming experience on par with enthusiast gaming PCs, but at a much lower cost through LiquidSky’s low-cost and free subscription models.
  • Gamers across the world can benefit from the exceptional GPU performance by connecting to any of the 13 LiquidSky global data centers.

Be sure to read our AMD Vega articles – The AMD Vega GPU Architecture Tech Report, Watch AMD Vega Run DOOM On Vulkan!, The AMD Vega Memory Architecture Q&A.

AMD and Developer Partners Embrace Forward Rendering in Unreal Engine 4

[adrotate group=”2″]
  • VR developers today are constantly challenged to strike the right mix of technical features and computational power for the best balance of performance and visual fidelity.
  • Deferred rendering, used by many of today’s big game engines, does all of the geometry work first and then shades pixels last to save work but it’s not a great fit for VR.
  • AMD is working to enable a forward rendering path in Unreal Engine 4.15, giving developers more choice in how they develop VR games and helping to achieve a stunning looking game while delivering the high frame rates necessary for a good experience.
  • AMD is also working with leading game developers to explore the benefits of forward rendering in VR games, including Survios, First Contact Entertainment and Limitless Studios.

Go Back To > Computer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The Complete AMD Radeon Instinct Tech Briefing Rev. 3.0

The AMD Tech Summit held in Sonoma, California from December 7-9, 2016 was not only very exclusive, it was highly secretive. The first major announcement we have been allowed to reveal is the new AMD Radeon Instinct heterogenous computing platform.

In this article, you will hear from AMD what the Radeon Instinct platform is all about. As usual, we have a ton of videos from the event, so it will be as if you were there with us. Enjoy! 🙂

Originally published @ 2016-12-12

Updated @ 2017-01-11 : Two of the videos were edited to comply with the NDA. Now that the NDA on AMD Vega has been lifted, we replaced the two videos with their full, unedited versions. We also made other changes, including adding links to the other AMD Tech Summit articles.

Updated @ 2017-01-20 : Replaced an incorrect slide, and a video featuring that slide. Made other small updates to the article.

 

The AMD Radeon Instinct Platform Summarised

For those who want the quick low-down on AMD Radeon Instinct, here are the key takeaway points :

  • The AMD Radeon Instinct platform is made up of two components – hardware and software.
  • The hardware components are the AMD Radeon Instinct accelerators built around the current Polaris and the upcoming Vega GPUs.
  • The software component is the AMD Radeon Open Compute (ROCm) platform, which includes the new MIOpen open-source deep learning library.
  • The first three Radeon Instinct accelerator cards are the MI6, MI8 and MI25 Vega with NCU.
  • The AMD Radeon Instinct MI6 is a passively-cooled inference accelerator with 5.7 TFLOPS of FP16 processing power, 224 GB/s of memory bandwidth, and a TDP of <150 W. It will come with 16 GB of GDDR5 memory.
  • The AMD Radeon Instinct MI8 is a small form-factor (SFF) accelerator with 8.2 TFLOPS of processing power, 512 GB/s of memory bandwidth, and a TDP of <175 W. It will come with 4 GB of HBM memory.
  • The AMD Radeon Instinct MI25 Vega with NCU is a passively-cooled training accelerator with 25 TFLOPS of processing power, support for 2X packed math, a High Bandwidth Cache and Controller, and a TDP of <300 W.
  • The Radeon Instinct accelerators will all be built exclusively by AMD.
  • The Radeon Instinct accelerators will all support MxGPU SRIOV hardware virtualisation.
  • The Radeon Instinct accelerators are all passively cooled.
  • The Radeon Instinct accelerators will all have large BAR (Base Address Register) support for multiple GPUs.
  • The upcoming AMD Zen “Naples” server platform is designed to supported multiple Radeon Instinct accelerators through a high-speed network fabric.
  • The ROCm platform is not only open source, it will support a multitude of standards in addition to MIOpen.
  • The MIOpen deep learning library is open source, and will be available in Q1 2017.
  • The MIOpen deep learning library is optimised for Radeon Instinct, allowing for 3X better performance in machine learning.
  • AMD Radeon Instinct accelerators will be significantly faster than NVIDIA Titan X GPUs based on the Maxwell and Pascal architectures.

In the subsequent pages, we will give you the full low-down on the Radeon Instinct platform, with the following presentations by AMD :

[adrotate banner=”4″]

We also prepared the complete video and slides of the Radeon Instinct tech briefing for your perusal :

Next Page > Heterogenous Computing, The Radeon Instinct Accelerators, MIOpen, Performance

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Why Is Heterogenous Computing Important?

Dr. Lisa Su, kicked things off with an inside look at her two-year long journey as AMD President and CEO. Then she revealed why Heterogenous Computing is an important part of AMD’s future going forward. She also mentioned the success of the recently-released Radeon Software Crimson ReLive Edition.

 

Here Are The New AMD Radeon Instinct Accelerators!

Next, Raja Koduri, Senior Vice President and Chief Architect of the Radeon Technologies Group, officially revealed the new AMD Radeon Instinct accelerators.

 

The MIOpen Deep Learning Library For Radeon Instinct

MIOpen is a new deep learning library optimised for Radeon Instinct. It is open source and will become part of the Radeon Open Compute (ROCm) platform. It will be available in Q1 2017.

[adrotate banner=”5″]

 

The Performance Advantage Of Radeon Instinct & MIOpen

MIOpen is optimised for Radeon Instinct, offering 3X better performance in machine learning. It allows the Radeon Instinct accelerators to be significantly faster than NVIDIA Titan X GPUs based on the Maxwell and Pascal architectures.

Next Page > Radeon Instinct MI25 & MI8 Demos, Zen “Naples” Platform, The First Servers, ROCm Discussion

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The Radeon Instinct MI25 Training Demonstration

Raja Koduri roped in Ben Sander, Senior Fellow at AMD, to show off the Radeon Instinct MI25 running a training demo.

 

The Radeon Instinct MI8 Visual Inference Demonstration

The visual inference demo is probably much easier to grasp, as it is visual in nature. AMD used the Radeon Instinct MI8 in this example.

 

The Radeon Instinct On The Zen “Naples” Platform

The upcoming AMD Zen “Naples” server platform is designed to supported multiple AMD Radeon Instinct accelerators through a high-speed network fabric.

[adrotate banner=”5″]

 

The First Radeon Instinct Servers

This is not a vapourware launch. Raja Koduri revealed the first slew of Radeon Instinct servers that will hit the market in H1 2017.

 

The Radeon Open Compute (ROCm) Platform Discussion

To illustrate the importance of heterogenous computing on Radeon Instinct, Greg Stoner (ROCm Senior Director at AMD), hosted a panel of AMD partners and early adopters in using the Radeon Open Compute (ROCm) platform.

Next Page > Closing Remarks On Radeon Instinct, The Complete Radeon Instinct Tech Briefing Video & Slides

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Closing Remarks On Radeon Instinct

Finally, Raja Koduri concluded the launch of the Radeon Instinct Initiative with some closing remarks on the recent Radeon Software Crimson ReLive Edition.

 

The Complete AMD Radeon Instinct Tech Briefing

This is the complete AMD Radeon Instinct tech briefing. Our earlier video was edited to comply with the AMD Vega NDA (which has now expired).

[adrotate banner=”5″]

 

The Complete AMD Radeon Instinct Tech Briefing Slides

Here are the Radeon Instinct presentation slides for your perusal.

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

Watch AMD Vega Run DOOM On Vulkan!

AMD recently revealed architectural details of the upcoming Vega GPU, but many people were disappointed that AMD is not ready to launch it yet. Will it matter how fantastic AMD Vega is on paper if it’s nowhere close to reality? The good news is AMD appears to be close to the final silicon.

In fact, at the AMD Tech Summit in Sonoma, we were shown an AMD Vega prototype running DOOM on Vulkan. Billy Khan from id Software also came to vouch for the performance and stability of the latest Vega silicon.

 

Watch AMD Vega Run DOOM On Vulkan!

AMD showed off this Vega prototype running DOOM at the 4K resolution of 3840 x 2160, using the Ultra Quality preset. DOOM was running with the Vulkan upgrade, of course, which allows for asynchronous compute. The video shows the Vega prototype deliver frame rates of 60-70 fps, with an average of 65 fps.

We tried to take a closer look inside the chassis to catch a look of the AMD Vega graphics card, but it appears to be well-shielded from our view. All we can say is that the card appears to be rather quiet… at least it was not audible in the hubbub of the room.

 

id Software On AMD Vega And Vulkan

Earlier that day, Billy Khan (Lead Project Programmer of id Tech 6 and DOOM) spoke about AMD Vega and Vulkan. Here are the key takeaway points :

[adrotate group=”2″]
  • Vulkan brings “close to the metal” coding to the PC
  • This allows for closer development of console and PC games
  • Micro-optimisations are now very easy to port from consoles to PC
  • They have been running DOOM at 4K on super high quality at over 70 fps on an early (few weeks old) AMD Vega silicon

We came away with the feeling that Billy was very impressed with the performance and stability of the Vega GPU. Hopefully, this will assuage the frustrations of AMD fans who are eager to see the AMD Vega to take on the NVIDIA Pascal…

 

The AMD Vega Launch Date

Right now, AMD will not reveal how close they are to the final silicon. Only that they aim to launch Vega in the first half of 2017.

For more information on AMD Vega, take a look at our AMD Vega GPU Architecture Tech Report.

Go Back To > Computer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The AMD Vega GPU Architecture Tech Report

We can reveal the fourth and, arguably, the biggest news out of the AMD Tech Summit that was held in Sonoma, California from December 7-9, 2016 – details of the new AMD Vega GPU architecture!

In this article, we will reveal to you, the details of not just the Vega NCU (Next-Gen Compute Unit) and the HBM2 memory it uses, but also its spanking new High-Bandwidth Cache Controller. On top of that, we will delve into the new geometry pipeline and pixel engine!

As usual, we will offer you a summary of the key points, and greater details in the subsequent pages. Finally, we will give you the presentation slides and when we get it, the presentation video from the AMD Tech Summit in Sonoma.

 

The 4 Major Features In AMD Vega

As AMD’s next-generation GPU architecture, Vega will come with these 4 major features that will help it to leapfrog ahead of competing graphics architectures.

We will summarise the key points below. But for more details, click on the links above.

 

High-Bandwidth Cache

[adrotate group=”2″]
  • High-Bandwidth Cache = HBM2 memory + High-Bandwidth Cache Controller (HBCC)
  • HBM2 memory technology offers :
    • 2X bandwidth per pin over HBM
    • 5X power efficiency over GDDR5
    • 8X capacity / stack
    • Over 50% smaller footprint compared to GDDR5
  • The High-Bandwidth Cache Controller offers :
    • Access to 512 TB virtual address space
    • Adaptive, fine-grained data movement
  • AMD showcased the performance of the High-Bandwidth Cache using a real-time render of Joe Macri’s living room on Radeon ProRender with 700+ GB of data

 

New Programmable Geometry Pipeline

  • The new AMD Vega geometry pipeline has over 2X peak throughput per clock
  • There is a new primitive shader that allows primitives to be discarded at a high rate
  • A new Intelligent Workgroup Distributor allows for improved load balancing

 

Next-Generation Compute Unit (NCU)

  • The AMD Vega NCU has configurable precision, allowing it to process :
    • 512 8-bits ops per clock, or
    • 256 16-bit ops per clock, or
    • 128 32-bit ops per clock
  • It is also optimised for higher clock speeds and higher IPC
  • It boasts a larger instruction buffer, and higher clock speeds

 

Next-Generation Pixel Engine

  • The AMD Vega pixel engine has a new Draw Stream Binning Rasteriser
  • The new rasteriser is designed to improve performance while saving power
  • The on-chip bin cache allows the rasteriser to only “fetch once”
  • The rasteriser also “shade once” by culling pixels invisible in the final scene
  • The render back-ends are now clients of the L2 cache, which improves deferred shading performance

 

I Want To Know More!

If you would like to know more about the four main improvements in the AMD Vega GPU architecture, please click on the following links, or just go on to the next page.

Next Page > High-Bandwidth Cache, HBM2 Memory, Cache Controller, Why Is It Called A Cache?

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

High-Bandwidth Cache

AMD Vega will use HBM2 memory, as well as a new High-Bandwidth Cache Controller (HBCC). Together, they are known as the High Bandwidth Cache.

AMD showcased the performance of the High-Bandwidth Cache using a real-time render of Joe Macri’s living room on Radeon ProRender with 700+ GB of data. Although no frame rate was visible, the real-time render appeared to be very smooth.

 

The HBM2 Memory

HBM2 offers twice the transfer rate per pin (up to 2 GT/s), over its the first-generation HBM memory. This allows it to achieve up to 256 GB/s memory bandwidth per package.

In both HBM and HBM2, up to 8 memory dies can be stacked in a package. But moving to HBM2 allows for twice the memory density – up to 8 GB per package is now possible.

 

The High-Bandwidth Cache Controller

The second component of the High Bandwidth Cache is the new High-Bandwidth Cache Controller (HBCC). It creates a homogenous memory system for the AMD Vega GPU, with up to 512 TB of addressable memory.

It also allows for the adaptive, fine-grained movement of data between the AMD Vega GPU and the system memory, the NVRAM and the network storage (as part of Infinity Fabric).

 

Why Is It Called A Cache?

AMD calls the combination of the HBM2 memory and the High-Bandwidth Cache Controller the “High-Bandwidth Cache“. Techies may wonder why AMD chose to call it “cache”, instead of “memory”. After all, HBM2 memory is a type of fast graphics memory.

[adrotate group=”2″]

The answer lies in the AMD Vega’s heterogenous memory system. All memory in the system, whether it’s the HBM2 memory or shared memory from the computer’s SDRAM, is seen as a contiguous memory space. A big block of memory, irrespective of how fast they are.

That may be great for memory addressing, but may cause frequently-used data to be placed in slower memory. To avoid such an occurrence, the High-Bandwidth Cache Controller uses the HBM2 memory like a fast cache. This allows it to keep the most frequently-used data in the fastest memory available – the HBM2 memory.

Hence, the HBM2 memory functions like a cache in AMD Vega, and that is why AMD called the combination the High-Bandwidth Cache.

Next Page > New AMD Vega Geometry Pipeline, Compute Unit & Pixel Engine

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The New Programmable Geometry Pipeline

The AMD Vega features a new programmable geometry pipeline. It boasts over twice the peak throughput per clock, compared to the previous-generation geometry pipeline. This is achieved through two new improvements – primitive shaders and the Intelligent Workgroup Distributor.

The primitive shader stage is a completely new addition. It allows for primitives to be discarded at a much higher rate. The Intelligent Workgroup Distributor, on the other hand, improves the load balancing of work going to the large number of pipelines.

 

The Next-Generation Compute Unit (NCU)

The AMD Vega NCU is optimised for higher clock speeds, and higher IPC. It boasts a larger instruction buffer, and naturally – high clock speeds. But what’s unique is its flexible, configurable precision. This allows it to process, not just 64-bit and 32-bit operations, but also 16-bit and 8-bit operations. For example, the AMD Vega NCU can process :

  • 512 8-bits ops per clock, or
  • 256 16-bit ops per clock, or
  • 128 32-bit ops per clock

The Vega NCU does not “waste” computing power by only allowing one operation per clock. If it is a smaller-sized operation, it can be combined to maximise performance. This allows it to boost the performance of “packed math” applications.

This is how the new Radeon Instinct MI25 Vega accelerators deliver 25 teraflops of FP16 compute performance. You can read more about Radeon Instinct in the following articles :

[adrotate group=”1″]

 

The Next-Generation Pixel Engine

The AMD Vega pixel engine has a new Draw Stream Binning Rasteriser. It is designed to improve performance while saving power. The on-chip bin cache allows it to only “fetch once“, and it culls pixels invisible to the final scene so it can also “shade once“.

In previous GPU architectures, the pixel and texture memory accesses are non-coherent. That means the same data required by both pixel and texture shaders are not “visible”, and have to be fetched and flushed independently. This reduces efficiency and wastes cache bandwidth.

In the AMD Vega GPU, the homogenous memory system allows for coherent memory accesses. In addition, the render back-ends are now clients of the L2 cache. This allows data to remain in the L1 and L2 caches, and not get flushed and refetched over and over again.

Next Page > The Complete AMD Vega GPU Architecture Slides

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The Complete AMD Vega GPU Architecture Slides

Here is the full set of official AMD slides on the AMD Vega GPU architecture for your perusal :

We hope to get our hands on the two AMD video presentations on the Vega GPU at the AMD Tech Summit. If we do get them, we will post them here. So check back later! 🙂

[adrotate group=”1″]

Go Back To > First PageComputer Hardware + Systems | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

The First AMD Radeon Instinct Servers Revealed!

When AMD launched Radeon Instinct at the 2016 AMD Tech Summit in Sonoma earlier this month, they showed off several servers that will be powered by the new Radeon Instinct accelerators. These Radeon Instinct servers can now deliver up to 3 petaflops (3,000 TFLOPS) of FP16 compute performance using those Radeon Instinct accelerators.

Most of the performance boost comes from the combination of the new Vega GPU architecture, which allows for 2X packed FP16 math ops; and the new AMD MIOpen deep learning library.

After the launch event, we were given the opportunity to look inside two of these servers – the Supermicro 1028GQ-TRT and the Invented K888 G3. Both of these servers will ship with multiple Radeon Instinct MI25 Vega with NCU accelerators, allowing them to deliver up to 100 TFLOPS of FP16 compute performance.

We also had a look at the Falconwitch PS1816 server which can host a whopping 16 Radeon Instinct MI25 Vega with NCU accelerators to deliver 300 teraflops of FP16 compute performance!

 

The Supermicro 1028GQ-TRT

This is the server Ben Sander used to demonstrate the training capability of the Radeon Instinct MI25 accelerator in the 2016 AMD Tech Summit.

The Supermicro 1028GQ-TRT is a 1U server that fits up to 3 Radeon Instinct MI25 Vega with NCU accelerators. That allows it to deliver up to 75 teraflops of FP16 compute performance.

Multiple servers can be combined to increase compute performance. In his demo, Ben Sander used two of these Supermicro servers to obtain 150 teraflops of computing performance.

 

The Inventec K888 G3

The Inventec K888 G3 is a 2U, 2-processor server that fits up to 4 Radeon Instinct MI25 Vega with NCU accelerators. This allows it to deliver up to 100 teraflops of FP16 compute performance.

In this example, the Inventec K888 is powered by four FirePro S9300 X2 cards instead. Each of these FirePro S9300 X2 cards deliver slightly more FP16 compute performance than the Radeon Instinct MI25 Vega, [adrotate banner=”5″]

 

The Falconwitch PS1816

The Falconwitch PS1816 is a 2U, 24-bay server that boasts a total of 288 PCIe lanes. This allows it to support up to sixteen Radeon Instinct MI25 Vega with NCU accelerators to deliver 400 teraflops of FP16 compute performance.

If that’s not enough, there is an Inventec Radeon Instinct 42U rack that features six of these Falconwitch PS1816 servers and an additional four Radeon Instinct MI25 Vega with NCU accelerators. That is a total of 120 Radeon Instinct MI25 accelerators, delivering 3,000 teraflops or 3 petaflops of FP16 compute performance! This is literally, the mother of all Radeon Instinct servers!

 

Raja Koduri Introducing The First Radeon Instinct Servers

For those who missed our complete coverage of Radeon Instinct, here is the video of Radeon Technologies Group Senior Vice President and Chief Architect, Raja Koduri introducing the first Radeon Instinct servers.

For more information on the Radeon Instinct accelerators, and MIOpen deep learning library, please take a look at our article – The Complete AMD Radeon Instinct Tech Briefing!

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!