AMD Instinct MI300A vs AMD Viola Full Specs

Summary

14,592 Shaders 2.1GHz	3,840 Shaders 2.23GHz
128GB HBM35.33TB/s	Shared Memory
Peak·FP32·FP16 122.6 TFLOPS	Peak·FP32·FP16 34.3 TFLOPS
Form Factor APU SH5 Socket	Form Factor iGPU
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 MI300A3.92 POPSINT4 Tensor Sparse

x57.18

Viola68.6 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed2100MHz UC·Base·Boost·OC	Clock Speed2233MHz UC·Boost·OC
Peak OPS 3.92 POPSINT4 Tensor Sparse	Peak OPS 68.6 TFLOPSFP16
Tensor FP8-16 1.96 PFLOPS FP8-16 Tensor Sparse 3.92 PFLOPS Tensor FP8-32 1.96 PFLOPS FP8-32 Tensor Sparse 3.92 PFLOPS	-
Tensor FP16-16 980.6 TFLOPS FP16-16 Tensor Sparse 1.96 PFLOPS Tensor FP16-32 980.6 TFLOPS FP16-32 Tensor Sparse 1.96 PFLOPS	-
BF16 - Tensor BF16 980.6 TFLOPS BF16 Tensor Sparse 1.96 PFLOPS	BF16 68.6 TFLOPS Tensor BF16 - BF16 Tensor Sparse -
Tensor TF32 490.3 TFLOPS	Tensor TF32 -
FP32 122.6 TFLOPS Tensor FP32 122.6 TFLOPS	FP32 34.3 TFLOPS Tensor FP32 -
FP64 61.29 TFLOPS Tensor FP64 122.6 TFLOPS	FP64 1.07 TFLOPS Tensor FP64 -
Tensor INT4 1.96 POPS	Tensor INT4 -
Tensor INT8 1.96 POPS	-
Pixel Rate -	Pixel Rate 214.4 GPixel/s
Texture Rate 1.92 TTexel/s	Texture Rate 535.9 GTexel/s

Core Config

Shaders 14,592 Shaders	Shaders 3,840 Shaders
TMUs 912 TMUs	TMUs 240 TMUs
ROPs -	ROPs 96 ROPs
Tensor Cores 912 T-Cores	Tensor Cores -
RT Cores -	RT Cores 60 RT-Cores
CUs 228 CUs	CUs 60 CUs

Clocks

Base Clock 1GHz	Base Clock -
Boost Clock 2.1GHz	Boost Clock 2.23GHz

Cache

L1 16KB/CU	L1 -
L2 Cache 16MB shared	L2 Cache 4MB shared
L3 Cache 192MB shared	L3 Cache -

Memory

128GB HBM3	Shared Memory
Memory Bus 8192-bit	Memory Bus 256-bit
Memory Speed 5.2GT/s	Memory Speed 18GT/s
Memory Bandwidth 5.33TB/s	Memory Bandwidth 576GB/s
ECC Yes	ECC No

Power & Thermals

TDP 560W

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

Decoder

Decoder 2x VCN 2.6

-

Card

Form Factor APU SH5 Socket	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 3	Architecture RDNA 4
Family Instinct	Family Console
Branding	Branding
Codename Aqua Vanjaram	Codename -
Chip Variant Aqua Vanjaram XT	Chip Variant -
Market Segment Server	Market Segment Console
Release Date Dec 6, 2023	Release Date Sep 10, 2024

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries TSMCActive Interposer	Other Foundries -
Fabrication Node N5 N6Active Interposer	Fabrication Node N6 -
Die Size 1110mm²	Die Size 260mm²
Transistor Count 109.5B	Transistor Count 10.6B
Transistor Density 98.65 MTr/mm²	Transistor Density 41 MTr/mm²

Images