AMD Instinct MI250 vs AMD Van Gogh Full Specs

Summary

13,312 Shaders 1.7GHz	512 Shaders 1.6GHz
128GB HBM2e3.28TB/s placeholder	Shared Memory88GB/sLPDDR5
Peak·FP32·FP16 45.26 TFLOPS	Peak·FP32·FP16 1.64 TFLOPS
Form Factor OAM Module	Form Factor iGPU
TDP 500W	TDP Shared

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 Tensor FP16-32 Tensor FP32 FP64 Tensor FP64 Tensor BF16 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Instinct MI250362.1 TOPSINT4 Tensor

x110.50

Van Gogh3.28 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed1700MHz UC·Base·Boost·OC	Clock Speed1600MHz UC·Base·Boost·OC
Peak OPS 362.1 TOPSINT4 Tensor	Peak OPS 3.28 TFLOPSFP16
Tensor FP16-16 362.1 TFLOPS Tensor FP16-32 362.1 TFLOPS	-
Tensor BF16 362.1 TFLOPS	-
FP32 45.26 TFLOPS Tensor FP32 90.52 TFLOPS	FP32 1.64 TFLOPS Tensor FP32 -
FP64 45.26 TFLOPS Tensor FP64 90.52 TFLOPS	FP64 102.4 GFLOPS Tensor FP64 -
Tensor INT4 362.1 TOPS	Tensor INT4 -
Tensor INT8 362.1 TOPS	-
Pixel Rate -	Pixel Rate 12.8 GPixel/s
Texture Rate 1.41 TTexel/s	Texture Rate 51.2 GTexel/s

Core Config

Shaders 13,312 Shaders	Shaders 512 Shaders
TMUs 832 TMUs	TMUs 32 TMUs
ROPs -	ROPs 8 ROPs
Tensor Cores 832 T-Cores	Tensor Cores -
CUs 208 CUs	CUs 8 CUs

Clocks

Base Clock 1GHz	Base Clock 1GHz
Boost Clock 1.7GHz	Boost Clock 1.6GHz

Cache

L0 Cache -	L0 Cache 32KB/WGP
L1 16KB/CU	L1 128KB/Array
L2 Cache 16MB shared	L2 Cache 1MB shared
L3 Cache -	L3 Cache 8MB shared
L3 Bandwidth -	L3 Bandwidth 208GB/s

Memory

128GB HBM2e placeholder	Shared MemoryLPDDR5
Memory Bus 8192-bit	Memory Bus 128-bit
Memory Speed 3.2GT/s	Memory Speed 5.5GT/s
Memory Bandwidth 3.28TB/s	Memory Bandwidth 88GB/s
ECC Yes	ECC No

Power & Thermals

TDP 500W

TDP Shared

Video Output

Max Resolution -	Max Resolution 3840x2160
Refresh Rate Calculator -	Refresh Rate Calculator 3840x2160 Resolution4K UHD Refresh Rate 60Hz
Multi-Monitor -	Multi-Monitor 1
DSC Not Supported	DSC Not Supported

API Support

OpenCL 3	-
GFX 9.4	-

Encoder

Encoder 2x VCN 2.6	Encoder VCN 3.0
Codec AVC (H.264) HEVC (H.265)	Codec AVC (H.264) HEVC (H.265)

Decoder

Decoder 2x VCN 2.6	Decoder VCN 3.0
Codec -	Codec MPEG-1 MPEG-2 MPEG-4 JPEG VC-1 VP9 AVC (H.264) HEVC (H.265) AV1

Card

Form Factor OAM Module	Form Factor iGPU
PCIe PCIe 4.0 x16	PCIe -
Cooling Passive	Cooling Open-Air
Multi-GPU Multi-GPU Support Supported Multi-GPU Type Infinity Fabric	Multi-GPU -

Chip

Manufacturer AMD	Manufacturer AMD
Chip Designer AMD	Chip Designer AMD
Architecture CDNA 2	Architecture RDNA 2
Family Instinct	Family Console
Branding	Branding
Codename Aldebaran	Codename -
Chip Variant Aldebaran XT	Chip Variant -
Market Segment Server	Market Segment Console
Release Date Nov 8, 2021	Release Date Feb 25, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N6	Fabrication Node N7
Die Size 1448mm²	Die Size 163mm²
Transistor Count 56B	Transistor Count 2.4B
Transistor Density 38.67 MTr/mm²	Transistor Density 15 MTr/mm²

Images