AMD Instinct MI325X vs AMD Radeon 660M 4CU 1800MHz Full Specs

Summary

19,456 Shaders 2.1GHz	256 Shaders 1.8GHz
288GB HBM3e6.01TB/s placeholder	Shared Memory76.8GB/s DDR5·LPDDR5
Peak·FP32·FP16 163.4 TFLOPS	Peak·FP32·FP16 921.6 GFLOPS
Form Factor OAM Module	Form Factor iGPU
TDP 560W	TDP Shared

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 MI325X5.23 POPSINT4 Tensor Sparse

x2837.33

Radeon 660M 4CU 1800MHz1.84 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed2100MHz UC·Base·Boost·OC	Clock Speed1800MHz UC·Base·Boost·OC
Peak OPS 5.23 POPSINT4 Tensor Sparse	Peak OPS 1.84 TFLOPSFP16
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 BF16 1.31 PFLOPS BF16 Tensor Sparse 2.62 PFLOPS	-
Tensor TF32 653.7 TFLOPS	Tensor TF32 -
FP32 163.4 TFLOPS Tensor FP32 163.4 TFLOPS	FP32 921.6 GFLOPS Tensor FP32 -
FP64 81.72 TFLOPS Tensor FP64 163.4 TFLOPS	FP64 57.6 GFLOPS Tensor FP64 -
Tensor INT4 2.62 POPS	Tensor INT4 -
Tensor INT8 2.62 POPS	-
Pixel Rate -	Pixel Rate 28.8 GPixel/s
Texture Rate 2.55 TTexel/s	Texture Rate 28.8 GTexel/s

Core Config

Shaders 19,456 Shaders	Shaders 256 Shaders
TMUs 1,216 TMUs	TMUs 16 TMUs
ROPs -	ROPs 16 ROPs
Tensor Cores 1,216 T-Cores	Tensor Cores -
RT Cores -	RT Cores 4 RT-Cores
CUs 304 CUs	CUs 4 CUs

Clocks

Base Clock 1GHz	Base Clock 1.5GHz
Boost Clock 2.1GHz	Boost Clock 1.8GHz

Cache

L1 16KB/CU	L1 -
L2 Cache 16MB shared	L2 Cache -
L3 Cache 256MB shared	L3 Cache -

Memory

288GB HBM3e placeholder	Shared Memory DDR5·LPDDR5
Memory Bus 8192-bit	Memory Bus 128-bit
Memory Speed 5.9GT/s	Memory Speed 4.8GT/s
Memory Bandwidth 6.01TB/s	Memory Bandwidth 76.8GB/s
ECC Yes	ECC -

Power & Thermals

TDP 560W

TDP Shared

Video Output

Multi-Monitor -	Multi-Monitor 4
DSC Not Supported	DSC -
HDCP -	HDCP HDCP 2.2

API Support

OpenCL 3	-
GFX 9.4	-

Encoder

Encoder 2x VCN 2.6	Encoder VCN 3.1
Codec AVC (H.264) HEVC (H.265)	Codec AVC (H.264) HEVC (H.265)

Decoder

Decoder 2x VCN 2.6	Decoder VCN 3.1
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 5.0 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 -
Architecture CDNA 3	Architecture -
Family Instinct	Family 600
Branding	Branding
Codename Aqua Vanjaram	Codename -
Chip Variant Aqua Vanjaram XTX	Chip Variant -
Market Segment Server	Market Segment Laptop
Release Date Jun 2, 2024	Release Date Sep 30, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries TSMCActive Interposer	Other Foundries -
Fabrication Node N5 N6Active Interposer	Fabrication Node N6 -
Die Size 1480mm²	Die Size 210mm²
Transistor Count 146B	Transistor Count 13.1B
Transistor Density 98.65 MTr/mm²	Transistor Density 62 MTr/mm²

Images