AMD Instinct MI250X vs AMD Radeon RX 6700S Full Specs

Summary

14,080 Shaders 1.7GHz	1,792 Shaders 2GHz
128GB HBM2e3.28TB/s	8GB GDDR6224GB/s
Peak·FP32·FP16 47.87 TFLOPS	Peak·FP32·FP16 7.17 TFLOPS
Form Factor OAM Module	Form Factor Soldered
TDP 560W	TDP 100W

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 MI250X383 TOPSINT4 Tensor

x26.71

Radeon RX 6700S14.34 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed1700MHz UC·Base·Boost·OC	Clock Speed2000MHz UC·Base·Boost·OC
Peak OPS 383 TOPSINT4 Tensor	Peak OPS 14.34 TFLOPSFP16
Tensor FP16-16 383 TFLOPS Tensor FP16-32 383 TFLOPS	-
Tensor BF16 383 TFLOPS	-
FP32 47.87 TFLOPS Tensor FP32 95.74 TFLOPS	FP32 7.17 TFLOPS Tensor FP32 -
FP64 47.87 TFLOPS Tensor FP64 95.74 TFLOPS	FP64 448 GFLOPS Tensor FP64 -
Tensor INT4 383 TOPS	Tensor INT4 -
Tensor INT8 383 TOPS	-
Pixel Rate -	Pixel Rate 128 GPixel/s
Texture Rate 1.5 TTexel/s	Texture Rate 256 GTexel/s

Core Config

Shaders 14,080 Shaders	Shaders 1,792 Shaders
TMUs 880 TMUs	TMUs 128 TMUs
ROPs -	ROPs 64 ROPs
Tensor Cores 880 T-Cores	Tensor Cores -
RT Cores -	RT Cores 28 RT-Cores
CUs 220 CUs	CUs 28 CUs

Clocks

Base Clock 1GHz	Base Clock 1.7GHz
Boost Clock 1.7GHz	Boost Clock 2GHz

Cache

L0 Cache -	L0 Cache 32KB/WGP
L1 16KB/CU	L1 128KB/Array
L2 Cache 16MB shared	L2 Cache 2MB shared
L3 Cache -	L3 Cache 32MB shared
L3 Bandwidth -	L3 Bandwidth 832GB/s

Memory

128GB HBM2e	8GB GDDR6
Memory Bus 8192-bit	Memory Bus 128-bit
Memory Speed 3.2GT/s	Memory Speed 14GT/s
Memory Bandwidth 3.28TB/s	Memory Bandwidth 224GB/s
ECC Yes	ECC No

Power & Thermals

TDP 560W

TDP 100W

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 -	Adaptive Sync FreeSync
DSC Not Supported	DSC Supported
HDCP -	HDCP HDCP 2.3

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
GFX 9.4	GFX 10.3

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 Soldered
PCIe PCIe 4.0 x16	PCIe PCIe 4.0 x8
Cooling Passive	Cooling Passive
Multi-GPU Multi-GPU Support Supported Multi-GPU Type Infinity Fabric	Multi-GPU Multi-GPU Support Supported Multi-GPU Type Bridgeless

Chip

Manufacturer AMD	Manufacturer AMD
Chip Designer AMD	Chip Designer AMD
Architecture CDNA 2	Architecture RDNA 2
Family Instinct	Family Radeon RX 6000
Branding	Branding
Codename Aldebaran	Codename Dimgrey Cavefish
Chip Variant Aldebaran XTX	Chip Variant Navi 23 XL
Market Segment Server	Market Segment Desktop
Release Date Nov 8, 2021	Release Date Jan 4, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N6	Fabrication Node N7
Die Size 1448mm²	Die Size 237mm²
Transistor Count 56B	Transistor Count 11.1B
Transistor Density 38.67 MTr/mm²	Transistor Density 46.67 MTr/mm²

Images