NVIDIA Hopper H100 With 4th Gen Tensor Core Is Twice As Fast Clock-For-Clock, Frequency Delivers 30% Performance Gain

NVIDIA Kepler GK110 GPU Is Equivalent To A Single GPC on Hopper H100 GPU, 4th Gen Tensor Cores Up To 2x Faster 1

NVIDIA is further dissecting its Hopper H100 GPU at Hot Chips 34, giving us a taste of what the 4th Gen Tensor Core architecture has to offer.

NVIDIA Kepler GK110 GPU Is Equivalent To A Single GPC on Hopper H100 GPU, 4th Gen Tensor Cores Up To 2x Faster

While AMD is taking the MCM approach on its HPC GPUs, NVIDIA has decided to stick with the monolithic design for now. Their Hopper H100, as such, is one of the biggest GPUs to be made using TSMC's 4N process node, a design that was optimized and made exclusively for NVIDIA.

Related StoryHassan Mujtaba
NVIDIA GeForce RTX 4090 CUDA Benchmark Shows A 60% Improvement Over The RTX 3090 Ti

The H100 GPU is a monster chip that comes packed with the latest 4nm tech and incorporates 80 Billion transistors along with the bleeding-edge HBM3 memory technology. The H100 is built upon the PG520 PCB board which has over 30 power VRMs & a massive integral interposer that uses TSMC's CoWoS tech to combine the Hopper H100 GPU with a 6-stack HBM3 design. Some of the main technologies of the Hopper H100 GPU include:

  • 132 SMs (2x Performance Per Clock)
  • 4th Gen Tensor Cores
  • Thread Block Clusters
  • 2nd Gen Multi-Instance GPU
  • Confidential Computing
  • PCIe Gen 5.0 Interface
  • World's First HBM3 DRAM
  • Larger 50 MB L2 Cache
  • 4th Gen NVLink (900 GB/s Total Bandwidth)
  • New SHARP support
  • NVLink Network

Out of the six stacks, two stacks are kept to ensure yield integrity. But the new HBM3 standard allows for up to 80 GB capacities at 3 TB/s speeds which are crazy. For comparison, the current fastest gaming graphics card, the RTX 3090 Ti, offers just 1 TB/s of bandwidth and 24 GB VRAM capacities. Other than that, the H100 Hopper GPU also packs in the latest FP8 data format, and through its new SXM connection, it helps accommodate the 700W power design that the chip is designed around. It also offers twice the FP32 and FP64 FMA rates and 256 KB L1 cache (shared memory).

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:

Related StoryJason R. Wilson
Intel XeSS Tested on NVIDIA & AMD GPUs, Arc Will Offer The Best Performance Scenario

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 and 60 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 Tesla Graphics CardNVIDIA H100 (SMX5)NVIDIA H100 (PCIe)NVIDIA A100 (SXM4)NVIDIA A100 (PCIe4)Tesla V100S (PCIe)Tesla V100 (SXM2)Tesla P100 (SXM2)Tesla P100
Tesla M40
Tesla K40
GPUGH100 (Hopper)GH100 (Hopper)GA100 (Ampere)GA100 (Ampere)GV100 (Volta)GV100 (Volta)GP100 (Pascal)GP100 (Pascal)GM200 (Maxwell)GK110 (Kepler)
Process Node4nm4nm7nm7nm12nm12nm16nm16nm28nm28nm
Transistors80 Billion80 Billion54.2 Billion54.2 Billion21.1 Billion21.1 Billion15.3 Billion15.3 Billion8 Billion7.1 Billion
GPU Die Size814mm2814mm2826mm2826mm2815mm2815mm2610 mm2610 mm2601 mm2551 mm2
FP32 CUDA Cores Per SM128128646464646464128192
FP64 CUDA Cores / SM128128323232323232464
FP32 CUDA Cores168961459269126912512051203584358430722880
FP64 CUDA Cores168961459234563456256025601792179296960
Tensor Cores528456432432640640N/AN/AN/AN/A
Texture Units528456432432320320224224192240
Boost ClockTBDTBD1410 MHz1410 MHz1601 MHz1530 MHz1480 MHz1329MHz1114 MHz875 MHz
TOPs (DNN/AI)2000 TOPs
4000 TOPs
1600 TOPs
3200 TOPs
1248 TOPs
2496 TOPs with Sparsity
1248 TOPs
2496 TOPs with Sparsity
130 TOPs125 TOPsN/AN/AN/AN/A
FP16 Compute2000 TFLOPs1600 TFLOPs312 TFLOPs
624 TFLOPs with Sparsity
312 TFLOPs
624 TFLOPs with Sparsity
32.8 TFLOPs30.4 TFLOPs21.2 TFLOPs18.7 TFLOPsN/AN/A
FP32 Compute1000 TFLOPs800 TFLOPs156 TFLOPs
(19.5 TFLOPs standard)
156 TFLOPs
(19.5 TFLOPs standard)
16.4 TFLOPs15.7 TFLOPs10.6 TFLOPs10.0 TFLOPs6.8 TFLOPs5.04 TFLOPs
FP64 Compute60 TFLOPs48 TFLOPs19.5 TFLOPs
(9.7 TFLOPs standard)
19.5 TFLOPs
(9.7 TFLOPs standard)
8.2 TFLOPs7.80 TFLOPs5.30 TFLOPs4.7 TFLOPs0.2 TFLOPs1.68 TFLOPs
Memory Interface5120-bit HBM35120-bit HBM2e6144-bit HBM2e6144-bit HBM2e4096-bit HBM24096-bit HBM24096-bit HBM24096-bit HBM2384-bit GDDR5384-bit GDDR5
Memory SizeUp To 80 GB HBM3 @ 3.0 GbpsUp To 80 GB HBM2e @ 2.0 GbpsUp To 40 GB HBM2 @ 1.6 TB/s
Up To 80 GB HBM2 @ 1.6 TB/s
Up To 40 GB HBM2 @ 1.6 TB/s
Up To 80 GB HBM2 @ 2.0 TB/s
16 GB HBM2 @ 1134 GB/s16 GB HBM2 @ 900 GB/s16 GB HBM2 @ 732 GB/s16 GB HBM2 @ 732 GB/s
12 GB HBM2 @ 549 GB/s
24 GB GDDR5 @ 288 GB/s12 GB GDDR5 @ 288 GB/s
L2 Cache Size51200 KB51200 KB40960 KB40960 KB6144 KB6144 KB4096 KB4096 KB3072 KB1536 KB

Products mentioned in this post

RTX 3090
USD 1,222
WccfTech Tv
Filter videos by