NVIDIA H100 SXM 80GB vs XFX Radeon RX 6600 Speedster SWFT 210 Full Specs

Summary

16,896 Shaders 1.98GHz	1,792 Shaders 2.49GHz
80GB HBM33.35TB/s	8GB GDDR6224GB/s
Peak·FP32·FP16 66.91 TFLOPS	Peak·FP32·FP16 8.93 TFLOPS
Form Factor SXM5	Form Factor PCIe Card
TDP 700W	TDP 132W
Power Connectors -	Power Connectors 1x 8-Pin

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 Tensor FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Memory Bandwidth TDP

H100 SXM 80GB3.96 POPSINT8 Tensor Sparse

x221.65

Radeon RX 6600 Speedster SWFT 21017.86 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed1980MHz UC·Base·Boost·OC	Clock Speed2491MHz UC·Base·Boost·OC
Peak OPS 3.96 POPSINT8 Tensor Sparse	Peak OPS 17.86 TFLOPSFP16
Tensor FP8-16 1.98 PFLOPS FP8-16 Tensor Sparse 3.96 PFLOPS Tensor FP8-32 1.98 PFLOPS FP8-32 Tensor Sparse 3.96 PFLOPS	-
Tensor FP16-16 989.4 TFLOPS FP16-16 Tensor Sparse 1.98 PFLOPS Tensor FP16-32 989.4 TFLOPS FP16-32 Tensor Sparse 1.98 PFLOPS	-
BF16 133.8 TFLOPS Tensor BF16 989.4 TFLOPS BF16 Tensor Sparse 1.98 PFLOPS	-
Tensor TF32 494.7 TFLOPS	Tensor TF32 -
FP32 66.91 TFLOPS	FP32 8.93 TFLOPS
FP64 33.45 TFLOPS Tensor FP64 61.84 TFLOPS	FP64 558 GFLOPS Tensor FP64 -
Tensor INT8 1.98 POPS	-
Pixel Rate 47.5 GPixel/s	Pixel Rate 159.4 GPixel/s
Texture Rate 1.04 TTexel/s	Texture Rate 279 GTexel/s

Core Config

Shaders 16,896 Shaders	Shaders 1,792 Shaders
TMUs 528 TMUs	TMUs 112 TMUs
ROPs 24 ROPs	ROPs 64 ROPs
Tensor Cores 528 T-Cores	Tensor Cores -
RT Cores -	RT Cores 28 RT-Cores
SMs 132 SMs	CUs 28 CUs

Clocks

Base Clock 1.06GHz	Base Clock 1.63GHz
Boost Clock 1.98GHz	Boost Clock 2.49GHz
Tensor Clock 1.83GHz	Tensor Clock -

Cache

L0 Cache -	L0 Cache 32KB/WGP
L1 64KB/SM Tex	L1 128KB/Array
L2 Cache 50MB shared	L2 Cache 2MB shared
L3 Cache -	L3 Cache 32MB shared
L3 Bandwidth -	L3 Bandwidth 832GB/s

Memory

80GB HBM3	8GB GDDR6
Memory Bus 5120-bit	Memory Bus 128-bit
Memory Speed 5.2GT/s	Memory Speed 14GT/s
Memory Bandwidth 3.35TB/s	Memory Bandwidth 224GB/s
ECC No	ECC No

Power & Thermals

TDP 700W	TDP 132W
Max Temp -	Max Temp 110°C Max

Video Output

Max Resolution -	Max Resolution 7680x4320
Refresh Rate Calculator -	Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 120Hz
Multi-Monitor -	Multi-Monitor 4
Adaptive Sync G-Sync FreeSync	Adaptive Sync - FreeSync
DSC Not Supported	DSC Supported
HDCP -	HDCP HDCP 2.3

Ports

-	3x DisplayPort 1.4 1x HDMI 2.1

API Support

Shader Model -	Shader Model 6.5
-	DirectX DirectX 12 Direct3D 12_2
OpenGL - OpenCL 3 Vulkan -	OpenGL 4.6 OpenCL 2.1 Vulkan 1.2
CUDA 9 GFX - PureVideo HD VP11 VDPAU Feature Set K	CUDA - GFX 10.3 PureVideo HD - VDPAU -

Encoder

-	Encoder VCN 3.0
Codec -	Codec AVC (H.264) HEVC (H.265)

Decoder

Decoder 7x NVDEC 5	Decoder VCN 3.0
Codec MPEG-1 MPEG-2 MPEG-4 - VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1	Codec MPEG-1 MPEG-2 MPEG-4 JPEG VC-1 - VP9 AVC (H.264) HEVC (H.265) AV1

Card

Form Factor SXM5	Form Factor PCIe Card
PCIe PCIe 5.0 x16 -	PCIe PCIe 4.0 x8 2-Slots
-	Height 131mm (5.16") Width 241mm (9.49") Depth 41mm (1.61")
Cooling Passive -	Cooling Open-Air 2x Fans
Power Connectors -	Power Connectors 1x 8-Pin
Multi-GPU Multi-GPU Support Supported Multi-GPU Type NVLink	Multi-GPU Multi-GPU Support Supported Multi-GPU Type Bridgeless

Chip

Manufacturer NVIDIA	Manufacturer XFX
Chip Designer NVIDIA	Chip Designer AMD
Architecture Hopper	Architecture RDNA 2
Family Server	Family Radeon RX 6000
Branding	Branding
Codename NV180	Codename Dimgrey Cavefish
Chip Variant -	Chip Variant Navi 23 XL
Market Segment Server	Market Segment Desktop
Release Date Mar 22, 2022	Release Date Aug 11, 2021

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4N	Fabrication Node N7
Die Size 814mm²	Die Size 237mm²
Transistor Count 80B	Transistor Count 11.1B
Transistor Density 98.28 MTr/mm²	Transistor Density 46.67 MTr/mm²

Images