AMD Instinct MI300P vs NVIDIA V100 SXM Full Specs

Summary

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

Instinct MI300P2.62 POPSINT4 Tensor Sparse

x20.86

V100 SXM125.3 TFLOPSFP16-16 Tensor

x1

Show Top Score

Theoretical Performance

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

Core Config

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

Clocks

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

Cache

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

Memory

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

Power & Thermals

TDP 300W

TDP 300W

Encoder

Encoder Model 2x VCN 2.6

Encoder Model 3x NVENC 5

Decoder

Decoder Model 2x VCN 2.6

Decoder Model NVDEC 3

Card

Form Factor OAM Module	Form Factor SXM3
Cooling Passive	Cooling Passive

Chip

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

Fabrication

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

Images

No images available

No images available

Competitors

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

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