NVIDIA V100 SXM vs AMD Instinct MI300P Full Specs

Summary

5,120 Shaders 1.53GHz	9,728 Shaders 2.1GHz
32GB HBM2896GB/s	64GB HBM32.66TB/s
Peak·FP32·FP16 15.67 TFLOPS	Peak·FP32·FP16 81.72 TFLOPS
Form Factor SXM3	Form Factor OAM Module
TDP 300W	TDP 300W

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 Tensor FP32 FP64 Tensor FP64 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

V100 SXM125.3 TFLOPSFP16-16 Tensor

x1

Instinct MI300P2.62 POPSINT4 Tensor Sparse

x20.86

Show Top Score

Theoretical Performance

Clock Speed1530MHz UC·Base·Boost·OC	Clock Speed2100MHz UC·Base·Boost·OC
Peak OPS 125.3 TFLOPSFP16-16 Tensor	Peak OPS 2.62 POPSINT4 Tensor Sparse
-	Tensor FP8-16 1.31 PFLOPS FP8-16 Tensor Sparse 2.62 PFLOPS Tensor FP8-32 1.31 PFLOPS FP8-32 Tensor Sparse 2.62 PFLOPS
Tensor FP16-16 125.3 TFLOPS FP16-16 Tensor Sparse - Tensor FP16-32 125.3 TFLOPS FP16-32 Tensor Sparse -	Tensor FP16-16 653.7 TFLOPS FP16-16 Tensor Sparse 1.31 PFLOPS Tensor FP16-32 653.7 TFLOPS FP16-32 Tensor Sparse 1.31 PFLOPS
-	Tensor BF16 653.7 TFLOPS BF16 Tensor Sparse 1.31 PFLOPS
Tensor TF32 -	Tensor TF32 326.9 TFLOPS
FP32 15.67 TFLOPS Tensor FP32 -	FP32 81.72 TFLOPS Tensor FP32 81.72 TFLOPS
FP64 7.83 TFLOPS Tensor FP64 -	FP64 40.86 TFLOPS Tensor FP64 81.72 TFLOPS
Tensor INT4 -	Tensor INT4 1.31 POPS
-	Tensor INT8 1.31 POPS
Pixel Rate 195.8 GPixel/s	Pixel Rate -
Texture Rate 489.6 GTexel/s	Texture Rate 1.28 TTexel/s

Core Config

Shaders 5,120 Shaders	Shaders 9,728 Shaders
TMUs 320 TMUs	TMUs 608 TMUs
ROPs 128 ROPs	ROPs -
Tensor Cores 640 T-Cores	Tensor Cores 608 T-Cores
SMs 80 SMs	CUs 152 CUs

Clocks

Base Clock 1.29GHz	Base Clock 1GHz
Boost Clock 1.53GHz	Boost Clock 2.1GHz

Cache

L2 Cache 6.1MB shared	L2 Cache 16.4MB shared
L3 Cache -	L3 Cache 128MB shared

Memory

32GB HBM2	64GB HBM3
Memory Bus 4096-bit	Memory Bus 4096-bit
Memory Speed 1.8GT/s	Memory Speed 5.2GT/s
Memory Bandwidth 896GB/s	Memory Bandwidth 2.66TB/s
ECC No	ECC Yes

Power & Thermals

TDP 300W

TDP 300W

Encoder

Encoder Model 3x NVENC 5

Encoder Model 2x VCN 2.6

Decoder

Decoder Model NVDEC 3

Decoder Model 2x VCN 2.6

Card

Form Factor SXM3	Form Factor OAM Module
Cooling Passive	Cooling Passive

Chip

Manufacturer NVIDIA	Manufacturer AMD
Chip Designer NVIDIA	Chip Designer AMD
Architecture Volta	Architecture CDNA 3
Family Server	Family Instinct
Branding	Branding
Codename NV140	Codename Aqua Vanjaram
Chip Variant GV100-400-A1	Chip Variant Aqua Vanjaram XL
Market Segment Server	Market Segment Server
Release Date Mar 27, 2018	Release Date Dec 6, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries -	Other Foundries TSMCActive Interposer
Fabrication Node 12FFN -	Fabrication Node N5 N6Active Interposer
Die Size 815mm²	Die Size 740mm²
Transistor Count 21.1 Billion	Transistor Count 73 Billion
Transistor Density 25.89 MTr/mm²	Transistor Density 98.65 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAV100 SXM vs GPU NVIDIAA800 40GB NVIDIAV100 SXM vs GPU NVIDIAA100 40GB NVIDIAV100 SXM vs GPU NVIDIAT40 Show 12 more

AMDInstinct MI300P vs GPU AMDInstinct MI200 AMDInstinct MI300P vs GPU AMDInstinct MI210 AMDInstinct MI300P vs GPU AMDInstinct MI300A Show 12 more