Tag Archives: AMD Instinct MI100

AMD, NVIDIA Banned From Selling AI Chips To China!

Both AMD and NVIDIA have just been banned from selling high-performance AI chips to both China and Russia!

Here is what you need to know…


AMD, NVIDIA Banned From Selling AI Chips To China + Russia!

On Friday, 26 August 2022, NVIDIA and AMD were both ordered by the US government to stop exporting high-performance AI chips to both China and Russia.

In its regulatory filing to the SEC, NVIDIA stated that the US government introduced this ban to prevent them from being used for military purposes, or by the Chinese or Russian military.

The ban uses the A100 Tensor Core GPU as the baseline for NVIDIA, and the 3rd Gen Instinct MI250 accelerator chip for AMD.

Effective immediately, anything equal to, or faster than, the NVIDIA A100 or the AMD Instinct MI250 can no longer be exported to either China or Russia. That includes the upcoming H100 chip.

On August 26, 2022, the U.S. government, or USG, informed NVIDIA Corporation, or the Company, that the USG has imposed a new license requirement, effective immediately, for any future export to China (including Hong Kong) and Russia of the Company’s A100 and forthcoming H100 integrated circuits.

DGX or any other systems which incorporate A100 or H100 integrated circuits and the A100X are also covered by the new license requirement.

The license requirement also includes any future NVIDIA integrated circuit achieving both peak performance and chip-to-chip I/O performance equal to or greater than thresholds that are roughly equivalent to the A100, as well as any system that includes those circuits. A license is required to export technology to support or develop covered products.

The USG indicated that the new license requirement will address the risk that the covered products may be used in, or diverted to, a ‘military end use’ or ‘military end user’ in China and Russia. The Company does not sell products to customers in Russia.

I should point out that the NVIDIA A100 was launched two years ago – on June 22, 2020, while the AMD Instinct MI250 was introduced on November 8, 2021.

So it appears that the US government wants to maintain at least a 1-year advantage in high-performance AI chips.


AMD, NVIDIA Set To Lose Billions From AI Chip Sales To China!

Both AMD and NVIDIA stopped selling chips to Russia, after the invasion of Ukraine, so there is no material loss from such a ban on sales to Russia.

However, they both stand to lose billions of dollars worth of sales to China. NVIDIA alone estimates that the ban will affect US$400 million of sales, just in the third fiscal quarter.

Even more worrying was the likelihood that this ban may delay the H100 chip’s launch, and force NVIDIA to move “certain operations” out of China.

The new license requirement may impact the Company’s ability to complete its development of H100 in a timely manner or support existing customers of A100 and may require the Company to transition certain operations out of China.

AMD however claims that the ban will not have a material impact on its business, because shipments of its less powerful MI100 chips are not affected.

At this time, we do not believe that shipments of MI100 integrated circuits are impacted by the new requirements.

We do not currently believe it is a material impact on our business.

Both AMD and NVIDIA will now have to discuss with their customers in China on using alternative (less powerful) chips, or obtaining special licenses from the US government.


Please Support My Work!

Support my work through a bank transfer /  PayPal / credit card!

Name : Adrian Wong
Bank Transfer : CIMB 7064555917 (Swift Code : CIBBMYKL)
Credit Card / Paypal : https://paypal.me/techarp

Dr. Adrian Wong has been writing about tech and science since 1997, even publishing a book with Prentice Hall called Breaking Through The BIOS Barrier (ISBN 978-0131455368) while in medical school.

He continues to devote countless hours every day writing about tech, medicine and science, in his pursuit of facts in a post-truth world.


Recommended Reading

Go Back To > Enterprise | ComputerTech ARP


Support Tech ARP!

Please support us by visiting our sponsors, participating in the Tech ARP Forums, or donating to our fund. Thank you!

AMD Instinct MI100 : 11.5 TFLOPS In A Single Card!

AMD just announced the Instinct MI100 – the world’s fastest HPC GPU accelerator, delivering 11.5 TFLOPS in a single card!


AMD Instinct MI100 : 11.5 TFLOPS In A Single Card!

Powered by the new CDNA architecture, the AMD Instinct MI100 is the world’s fastest HPC GPU, and the first to break the 10 TFLOPS FP64 barrier!

Compared to the last-generation AMD accelerators, the AMD Instinct MI100 offers HPC applications almost 3.5X faster performance (FP32 matrix), and AI applications nearly 7X boost in throughput (FP16).

  • up to 11.5 TFLOPS of FP64 performance for HPC
  • up to 46.1 TFLOPS of FP32 Matrix performance for AI and machine learning
  • up to 184.6 TFLOPS of FP16 performance for AI training

2nd Gen AMD Infinity Fabric

It also leverages on the 2nd Gen AMD Infinity Fabric technology to deliver twice the peer-to-peer IO bandwidth of PCI Express 4.0. Thanks to its triple Infinity Fabric Links, it offers up to 340 GB/s of aggregate bandwidth per card.

In a server, MI100 GPUs can be configured as two fully-connected quad GPU hives, each providing up to 552 GB/s of P2P IO bandwidth.

Ultra-Fast HBM2 Memory

The AMD Instinct MI100 comes with 32 GB of HBM2 memory that deliver up to 1.23 TB/s of memory bandwidth to support large datasets.

PCI Express 4.0 Interface

The AMD Instinct MI100 is supports PCI Express 4.0, allowing for up to 64 GB/s of peak bandwidth from CPU to GPU, when paired with 2nd Gen AMD EPYC processors.

AMD Instinct MI100 : Specifications

Specifications AMD Instinct MI100
Fab Process 7 nm
Compute Units 120
Stream Processors 7,680
Peak INT4 | INT8
Peak FP16
Peak FP32
Peak FMA32
Peak FP64 | FMA64
184.6 TOPS
184.6 TFLOPS
Memory 32 GB HBM2
Memory Interface 4,096 bits
Memory Clock 1.2 GHz
Memory Bandwidth 1.2 TB/s
Reliability Full Chip ECC
RAS Support
Scalability 3 x Infinity Fabric Links
OS Support Linux 64-bit
Bus Interface PCIe Gen 3 / Gen 4
Board Form Factor Full Height, Dual Slot
Board Length 10.5-inch long
Cooling Passively Cooled
Max Board Power 300 W TDP
Warranty 3-Years Limited


AMD Instinct MI100 : Availability

The AMD Instinct MI100 will be available in systems by the end of 2020 from OEM/ODM partners like Dell, Gigabyte, Hewlett Packard Enterprise (HPE), and Supermicro.


Recommended Reading

Go Back To > Enterprise ITComputer HardwareHome


Support Tech ARP!

If you like our work, you can help support us 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 CDNA Architecture : Tech Highlights!

In addition to the gaming-centric RDNA architecture, AMD just introduced a new CDNA architecture that is optimised for compute workloads.

Here are some key tech highlights of the new AMD CDNA architecture!


AMD CDNA Architecture : What Is It?

Unlike the fixed-function graphics accelerators of the past, GPUs are now fully-programmable accelerators using what’s called the GPGPU (General Purpose GPU) Architecture.

GPGPU allowed the industry to leverage their tremendous processing power for machine learning and scientific computing purposes.

Instead of continuing down the GPGPU path, AMD has decided to introduce two architectures :

  • AMD RDNA : optimised for gaming to maximise frames per second
  • AMD CDNA : optimised for compute workloads to maximise FLOPS per second.

Designed to accelerate compute workloads, AMD CDNA augments scalar and vector processing with new Matrix Core Engines, and adds Infinity Fabric technology for scale-up capability.

This allows the first CDNA-based accelerator – AMD Instinct MI100 – to break the 10 TFLOPS per second (FP64) barrier.

The GPU is connected to its host processor using a PCI Express 4.0 interface, that delivers up to 32 GB/s of bandwidth in both directions.


AMD CDNA Architecture : Compute Units

The command processor and scheduling logic receives API-level commands and translates them into compute tasks.

These compute tasks are implemented as compute arrays and managed by the four Asynchronous Compute Engines (ACE), which maintain their independent stream of commands to the compute units.

Its 120 compute units (CUs) are derived from the earlier GCN architecture, and organised into four compute engines that execute wavefronts that contain 64 work-items.

The CUs are, however, enhanced with new Matrix Core Engines, that are optimised for matrix data processing.

Here is the block diagram of the AMD Instinct MI100 accelerator, showing how its main blocks are all tied together with the on-die Infinity Fabric.

Unlike the RDNA architecture, CDNA removes all of the fixed-function graphics hardware for tasks like rasterisation, tessellation, graphics caches, blending and even the display engine.

CDNA retains the dedicated logic for HEVC, H.264 and VP9 decoding that is sometimes used for compute workloads that operate on multimedia data.

The new Matrix Core Engines add a new family of wavefront-level instructions – the Matrix Fused Multiply-Add (MFMA). The MFMA instructions perform mixed-precision arithmetic and operates on KxN matrices using four different types of input data :

  • INT8 – 8-bit integers
  • FP16 – 16-bit half-precision
  • bf16 – 16-bit brain FP
  • FP32 – 32-bit single-precision

The new Matrix Core Engines has several advantages over the traditional vector pipelines in GCN :

  • the execution unit reduces the number of register file reads, since many input values are reused in a matrix multiplication
  • narrower datatypes create opportunity for workloads that do not require full FP32 precision, e.g. machine learning – saving energy.


AMD CDNA Architecture : L2 Cache + Memory

Most scientific and machine learning data sets are gigabytes or even terabytes in size. Therefore L2 cache and memory performance is critical.

In CDNA, the L2 cache is shared across the entire chip, and physically partitioned into multiple slices.

The MI100, specifically, has an 8 MB cache that is 16-way set-associative and made up of 32 slices. Each slice can sustain 128 bytes for an aggregate bandwidth of over 6 TB/s across the GPU.

The CDNA memory controller can drive 4- or 8-stacks high of HBM2 memory at 2.4 GT/s for a maximum throughput of 1.23 TB/s.

The memory contents are also protected by hardware ECC.


AMD CDNA Architecture : Communication + Scaling

CDNA is also designed for scaling up, using the high-speed Infinity Fabric technology to connect multiple GPUs.

AMD Infinity Fabric links are 16-bits wide, and operate at 23 GT/s, with three links in CDNA to allow for full connectivity in a quad-GPU configuration.

While the last generation Radeon Instinct MI50 GPU only uses a ring topology, the new fully-connected Infinity Fabric topology boosts performance for common communication patterns like all-reduce and scatter / gather.

Unlike PCI Express, Infinity Fabric links support coherent GPU memory, which lets multiple GPUs share an address space and tightly work on a single task.


Recommended Reading

Go Back To > Enterprise ITComputer HardwareHome


Support Tech ARP!

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