AMD Instinct MI325X vs AMD Radeon RX 7900M Full Specs

Summary

19,456 Shaders 2.1GHz	4,608 Shaders 2.09GHz
288GB HBM3e6.01TB/s	16GB GDDR6576GB/s
Peak·FP32·FP16 163.4 TFLOPS	Peak·FP32·FP16 38.52 TFLOPS
Form Factor OAM Module	Form Factor Soldered
TDP 560W	TDP 180W

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

Instinct MI325X5.23 POPSINT4 Tensor Sparse

x33.94

Radeon RX 7900M154.1 TOPSINT4 Tensor

x1

Show Top Score

Theoretical Performance

Clock Speed2100MHz UC·Base·Boost·OC	Clock Speed2090MHz UC·Base·Boost·OC
Peak OPS 5.23 POPSINT4 Tensor Sparse	Peak OPS 154.1 TOPSINT4 Tensor
Tensor FP8-16 2.62 PFLOPS FP8-16 Tensor Sparse 5.23 PFLOPS Tensor FP8-32 2.62 PFLOPS FP8-32 Tensor Sparse 5.23 PFLOPS	-
Tensor FP16-16 1.31 PFLOPS FP16-16 Tensor Sparse 2.62 PFLOPS Tensor FP16-32 1.31 PFLOPS FP16-32 Tensor Sparse 2.62 PFLOPS	Tensor FP16-16 38.52 TFLOPS FP16-16 Tensor Sparse - Tensor FP16-32 38.52 TFLOPS FP16-32 Tensor Sparse -
BF16 - Tensor BF16 1.31 PFLOPS BF16 Tensor Sparse 2.62 PFLOPS	BF16 77.05 TFLOPS Tensor BF16 38.52 TFLOPS BF16 Tensor Sparse -
Tensor TF32 653.7 TFLOPS	Tensor TF32 -
FP32 163.4 TFLOPS Tensor FP32 163.4 TFLOPS	FP32 38.52 TFLOPS Tensor FP32 -
FP64 81.72 TFLOPS Tensor FP64 163.4 TFLOPS	FP64 1.2 TFLOPS Tensor FP64 -
Tensor INT4 2.62 POPS	Tensor INT4 154.1 TOPS
Tensor INT8 2.62 POPS	Tensor INT8 38.52 TOPS
Pixel Rate -	Pixel Rate 401.3 GPixel/s
Texture Rate 2.55 TTexel/s	Texture Rate 601.9 GTexel/s

Core Config

Shaders 19,456 Shaders	Shaders 4,608 Shaders
TMUs 1,216 TMUs	TMUs 288 TMUs
ROPs -	ROPs 192 ROPs
Tensor Cores 1,216 T-Cores	Tensor Cores 144 T-Cores
RT Cores -	RT Cores 72 RT-Cores
CUs 304 CUs	CUs 72 CUs

Clocks

Base Clock 1GHz	Base Clock 1.82GHz
Boost Clock 2.1GHz	Boost Clock 2.09GHz

Cache

L0 Cache -	L0 Cache 64KB/WGP
L1 16KB/CU	L1 256KB/Array
L2 Cache 16MB shared	L2 Cache 6MB shared
L3 Cache 256MB shared	L3 Cache 64MB shared
L3 Bandwidth -	L3 Bandwidth 2.33TB/s

Memory

288GB HBM3e	16GB GDDR6
Memory Bus 8192-bit	Memory Bus 256-bit
Memory Speed 5.9GT/s	Memory Speed 18GT/s
Memory Bandwidth 6.01TB/s	Memory Bandwidth 576GB/s
ECC Yes	ECC No

Power & Thermals

TDP 560W

TDP 180W

Video Output

Max Resolution -	Max Resolution 7680x4320
Refresh Rate Calculator -	Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 165Hz
Multi-Monitor -	Multi-Monitor 3
Adaptive Sync -	Adaptive Sync FreeSync
DSC Not Supported	DSC Supported
HDCP -	HDCP HDCP 2.3

API Support

Shader Model -	Shader Model 6.7
-	DirectX DirectX 12 Direct3D 12_2
OpenGL - OpenCL 3 Vulkan -	OpenGL 4.6 OpenCL 2.2 Vulkan 1.3
GFX 9.4	GFX 11

Encoder

Encoder 2x VCN 2.6	Encoder VCN 4.0
Codec - AVC (H.264) HEVC (H.265) -	Codec VP9 AVC (H.264) HEVC (H.265) AV1

Decoder

Decoder 2x VCN 2.6	Decoder VCN 4.0
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 5.0 x16	PCIe PCIe 4.0 x16
Cooling Passive	Cooling Open-Air
Multi-GPU Multi-GPU Support Supported Multi-GPU Type Infinity Fabric	Multi-GPU Multi-GPU Support Supported Multi-GPU Type CrossFire XDMA

Chip

Manufacturer AMD	Manufacturer AMD
Chip Designer AMD	Chip Designer AMD
Architecture CDNA 3	Architecture RDNA 3
Family Instinct	Family Radeon RX 7000
Branding	Branding
Codename Aqua Vanjaram	Codename Plum Bonito
Chip Variant Aqua Vanjaram XTX	Chip Variant Navi 31 XL
Market Segment Server	Market Segment Laptop
Release Date Jun 2, 2024	Release Date Oct 19, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries TSMCActive Interposer -	Other Foundries - TSMCMCD
Fabrication Node N5 N6Active Interposer -	Fabrication Node N5 - N6MCD
Die Size 1480mm² -	Die Size 304mm² 225mm²MCD
Transistor Count 146B -	Transistor Count 45.4B 12.3BMCD
Transistor Density 98.65 MTr/mm² -	Transistor Density 149.2 MTr/mm² 54.67 MTr/mm²MCD

Images