NVIDIA Hopper H100 GPU Specs Updated, Now Features Even Faster 67 TFLOPs FP32 Compute Horsepower
When NVIDIA announced its Hopper H100 GPU for AI Datacenters earlier this year, the company had published up to 60 TFLOPs FP32 and 30 TFLOPs FP64 figures. However, as the launch comes close, the company has now updated the specifications to reflect more realistic expectations and as it turns out, the flagship and fastest chip for the AI segment is, even more, faster now. One reason why the compute numbers have seen a boost is because when the chip goes through production, the GPU manufacturer can finalize the numbers based on actual clock speeds. It is likely that NVIDIA used conservative clock figures to provide the preliminary performance figures and as the production hit full swing, the company saw that the chip can offer much better clocks. Last month at GTC, NVIDIA confirmed that their Hopper H100 GPU was under full production and partners will be rolling out the first wave of products in October this year. It was also confirmed that the global rollout for Hopper will include three phases, the first will be pre-orders for NVIDIA DGX H100 systems & free hands of labs to customers directly from NVIDIA with systems such as Dell’s Power Edge servers which are now available on NVIDIA LaunchPad. NVIDIA Hopper H100 GPU Specifications At A Glance So coming to the specifications, the NVIDIA Hopper GH100 GPU is composed of a massive 144 SM (Streaming Multiprocessor) chip layout which is featured in a total of 8 GPCs. These GPCs rock total of 9 TPCs which are further composed of 2 SM units each. This gives us 18 SMs per GPC and 144 on the complete 8 GPC configuration. Each SM is composed of up to 128 FP32 units which should give us a total of 18,432 CUDA cores. Following are some of the configurations you can expect from the H100 chip: The full implementation of the GH100 GPU includes the following units:
8 GPCs, 72 TPCs (9 TPCs/GPC), 2 SMs/TPC, 144 SMs per full GPU 128 FP32 CUDA Cores per SM, 18432 FP32 CUDA Cores per full GPU 4 Fourth-Generation Tensor Cores per SM, 576 per full GPU 6 HBM3 or HBM2e stacks, 12 512-bit Memory Controllers 60 MB L2 Cache Fourth-Generation NVLink and PCIe Gen 5
The NVIDIA H100 GPU with SXM5 board form-factor includes the following units:
8 GPCs, 66 TPCs, 2 SMs/TPC, 132 SMs per GPU 128 FP32 CUDA Cores per SM, 16896 FP32 CUDA Cores per GPU 4 Fourth-generation Tensor Cores per SM, 528 per GPU 80 GB HBM3, 5 HBM3 stacks, 10 512-bit Memory Controllers 50 MB L2 Cache Fourth-Generation NVLink and PCIe Gen 5
This is a 2.25x increase over the full GA100 GPU configuration. NVIDIA is also leveraging more FP64, FP16 & Tensor cores within its Hopper GPU which would drive up performance immensely. And that’s going to be a necessity to rival Intel’s Ponte Vecchio which is also expected to feature 1:1 FP64. NVIDIA states that the 4th Gen Tensor Cores on Hopper deliver 2 times the performance at the same clock. The following NVIDIA Hopper H100 performance breakdown shows that the additional SMs are only a 20% performance increase. The main benefit comes from the 4th Gen Tensor Cores and the FP8 compute the path. Higher frequency also adds a decent 30% uplift to the mix. An interesting comparison that points out GPU scaling shows that a single GPC on a Hopper H100 GPU is equivalent to a Kepler GK110 GPU, a flagship HPC chip from 2012. The Kepler GK110 housed a total of 15 SMs whereas the Hopper H110 GPU packs 132 SMs and even a singular GPC on the Hopper GPU features 18 SMs, 20% more than the entirety of SMs on the Kepler flagship. The cache is another space where NVIDIA has given much attention, upping it to 48 MB in the Hopper GH100 GPU. This is a 20% increase over the 50 MB cache featured on the Ampere GA100 GPU and 3x the size of AMD’s flagship Aldebaran MCM GPU, the MI250X. Rounding up the performance figures, NVIDIA’s GH100 Hopper GPU will offer 4000 TFLOPs of FP8, 2000 TFLOPs of FP16, 1000 TFLOPs of TF32, 67 TFLOPs of FP32 and 34 TFLOPs of FP64 Compute performance. These record-shattering figures decimate all other HPC accelerators that came before it. For comparison, this is 3.3x faster than NVIDIA’s own A100 GPU and 28% faster than AMD’s Instinct MI250X in the FP64 compute. In FP16 compute, the H100 GPU is 3x faster than A100 and 5.2x faster than MI250X which is literally bonkers. The PCIe variant which is a cut-down model was recently listed over in Japan for over $30,000 US so one can imagine that the SXM variant with a beefier configuration will easily cost around $50 grand.
NVIDIA HPC / AI GPUs
News Source: Videocardz
