AMD Instinct MI350X vs AMD Viola Full Specs

Summary

16,384 Shaders 2.2GHz	3,840 Shaders 2.23GHz
288GB HBM3e8TB/s	Shared Memory
Peak·FP32·FP16 144.2 TFLOPS	Peak·FP32·FP16 34.3 TFLOPS
Form Factor OAM Module	Form Factor iGPU
TDP 1000W	TDP 180W

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP4 FP4 Tensor Sparse 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 INT8 Tensor INT4 Memory Bandwidth TDP

Instinct MI350X18.45 PFLOPSFP4 Tensor Sparse

x269.03

Viola68.6 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed2200MHz UC·Boost·OC	Clock Speed2233MHz UC·Boost·OC
Peak OPS 18.45 PFLOPSFP4 Tensor Sparse	Peak OPS 68.6 TFLOPSFP16
Tensor FP4 9.23 PFLOPS FP4 Tensor Sparse 18.45 PFLOPS	-
Tensor FP8-16 4.61 PFLOPS FP8-16 Tensor Sparse 9.23 PFLOPS Tensor FP8-32 4.61 PFLOPS FP8-32 Tensor Sparse 9.23 PFLOPS	-
Tensor FP16-16 2.31 PFLOPS FP16-16 Tensor Sparse 4.61 PFLOPS Tensor FP16-32 2.31 PFLOPS FP16-32 Tensor Sparse 4.61 PFLOPS	-
BF16 - Tensor BF16 2.31 PFLOPS BF16 Tensor Sparse 4.61 PFLOPS	BF16 68.6 TFLOPS Tensor BF16 - BF16 Tensor Sparse -
FP32 144.2 TFLOPS Tensor FP32 144.2 TFLOPS	FP32 34.3 TFLOPS Tensor FP32 -
FP64 72.09 TFLOPS Tensor FP64 72.09 TFLOPS	FP64 1.07 TFLOPS Tensor FP64 -
Tensor INT4 4.61 POPS	Tensor INT4 -
Tensor INT8 4.61 POPS	-
Pixel Rate -	Pixel Rate 214.4 GPixel/s
Texture Rate -	Texture Rate 535.9 GTexel/s

Core Config

Shaders 16,384 Shaders	Shaders 3,840 Shaders
TMUs -	TMUs 240 TMUs
ROPs -	ROPs 96 ROPs
Tensor Cores 1,024 T-Cores	Tensor Cores -
RT Cores -	RT Cores 60 RT-Cores
CUs 256 CUs	CUs 60 CUs

Clocks

Boost Clock 2.2GHz

Boost Clock 2.23GHz

Cache

L1 16KB/CU	L1 -
L2 Cache 16MB shared	L2 Cache 4MB shared
L3 Cache 256MB shared	L3 Cache -

Memory

288GB HBM3e	Shared Memory
Memory Bus 8192-bit	Memory Bus 256-bit
Memory Speed 7.8GT/s	Memory Speed 18GT/s
Memory Bandwidth 8TB/s	Memory Bandwidth 576GB/s
ECC Yes	ECC No

Power & Thermals

TDP 1000W

TDP 180W

Video Output

Max Resolution -	Max Resolution 3840x2160
Refresh Rate Calculator -	Refresh Rate Calculator 3840x2160 Resolution4K UHD Refresh Rate 120Hz
Multi-Monitor -	Multi-Monitor 1
Adaptive Sync -	Adaptive Sync FreeSync
DSC Not Supported	DSC Not Supported

API Support

Shader Model -	Shader Model 6.5
OpenGL - OpenCL 3 Vulkan -	OpenGL 4.6 OpenCL 1.2 Vulkan 1.2
GFX 9.4	-

Encoder

Encoder 4x VCN 4.0	-
Codec VP9 AVC (H.264) HEVC (H.265) AV1	Codec -

Decoder

Decoder 4x VCN 4.0	-
Codec MPEG-1 MPEG-2 MPEG-4 JPEG VC-1 VP9 AVC (H.264) HEVC (H.265) AV1	Codec -

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 AMD
Architecture CDNA 4	Architecture RDNA 4
Family Instinct	Family Console
Branding	Branding
Codename CDNA Next	Codename -
Market Segment Server	Market Segment Console
Release Date Jun 12, 2025	Release Date Sep 10, 2024

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries TSMCIO	Other Foundries -
Fabrication Node N3P N6IO	Fabrication Node N6 -
Die Size 1448mm²	Die Size 260mm²
Transistor Count 139.2B 46BIO	Transistor Count 10.6B -
Transistor Density 96.13 MTr/mm²	Transistor Density 41 MTr/mm²

Images