AMD today announced the new AMD Instinct MI100 accelerator - the world's fastest HPC GPU and the first x86 server GPU to surpass the 10 teraflops (FP64) performance barrier. Supported by new accelerated compute platforms from Dell, Gigabyte, HPE, and Supermicro, the MI100, combined with AMD EPYC CPUs and the ROCm 4.0 open software platform, is designed to propel new discoveries ahead of the exascale era.

Built on the new AMD CDNA architecture, the AMD Instinct MI100 GPU enables a new class of accelerated systems for HPC and AI when paired with 2nd Gen AMD EPYC processors. The MI100 offers up to 11.5 TFLOPS of peak FP64 performance for HPC and up to 46.1 TFLOPS peak FP32 Matrix performance for AI and machine learning workloads. With new AMD Matrix Core technology, the MI100 also delivers a nearly 7x boost in FP16 theoretical peak floating point performance for AI training workloads compared to AMD's prior generation accelerators.

AMD today announced its Radeon Pro VII professional graphics card targeting 3D artists, engineering professionals, broadcast media professionals, and HPC researchers. The card is based on AMD's "Vega 20" multi-chip module that incorporates a 7 nm (TSMC N7) GPU die, along with a 4096-bit wide HBM2 memory interface, and four memory stacks adding up to 16 GB of video memory. The GPU die is configured with 3,840 stream processors across 60 compute units, 240 TMUs, and 64 ROPs. The card is built in a workstation-optimized add-on card form-factor (rear-facing power connectors and lateral-blower cooling solution).

What separates the Radeon Pro VII from last year's Radeon VII is full double precision floating point support, which is 1:2 FP32 throughput compared to the Radeon VII, which is locked to 1:4 FP32. Specifically, the Radeon Pro VII offers 6.55 TFLOPs double-precision floating point performance (vs. 3.36 TFLOPs on the Radeon VII). Another major difference is the physical Infinity Fabric bridge interface, which lets you pair up to two of these cards in a multi-GPU setup to double the memory capacity, to 32 GB. Each GPU has two Infinity Fabric links, running at 1333 MHz, with a per-direction bandwidth of 42 GB/s. This brings the total bidirectional bandwidth to a whopping 168 GB/s—more than twice the PCIe 4.0 x16 limit of 64 GB/s.