NVIDIA GA10B 32SM Full Specs

Summary

2,048 Shaders 1.3GHz

Shared Memory204.8GB/sLPDDR5

Peak·FP32·FP16 5.33 TFLOPS

Form Factor iGPU

TDP Shared

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth

GA10B 32SM340.8 TOPSINT4 Tensor Sparse

x1

Top Score3.35 PFLOPS FP4 Tensor SparseDesktop1xGeForce RTX 5090

x9.84

Theoretical Performance

Clock Speed1300MHz UC·Boost·OC

Peak OPS 340.8 TOPSINT4 Tensor Sparse

Tensor FP16-16 42.6 TFLOPS FP16-16 Tensor Sparse 85.2 TFLOPS Tensor FP16-32 42.6 TFLOPS FP16-32 Tensor Sparse 85.2 TFLOPS

Tensor BF16 42.6 TFLOPS BF16 Tensor Sparse 85.2 TFLOPS

Tensor TF32 21.3 TFLOPS

FP32 5.33 TFLOPS

Tensor INT4 170.4 TOPS

Tensor INT8 85.2 TOPS

Pixel Rate 41.6 GPixel/s

Texture Rate 20.8 GTexel/s

Core Config

Shaders 2,048 Shaders

TMUs 16 TMUs

ROPs 32 ROPs

Tensor Cores 64 T-Cores

SMs 16 SMs

Clocks

Boost Clock 1.3GHz

Cache

L1 64KB/SM Tex

L2 Cache 4MB shared

Memory

Shared MemoryLPDDR5

Memory Bus 256-bit

Memory Speed 6.4GT/s

Memory Bandwidth 204.8GB/s

ECC No

Video Output

Adaptive Sync G-Sync FreeSync

DSC Not Supported

API Support

Shader Model 6.7

DirectX DirectX 12 Direct3D 12_2

OpenGL 4.6 OpenCL 3 Vulkan 1.3

CUDA 8.7 PureVideo HD VP11 VDPAU Feature Set K

Encoder

Encoder NVENC 7

Codec AVC (H.264) HEVC (H.265)

Decoder

Decoder NVDEC 5

Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1

Card

Form Factor iGPU

Chip

Manufacturer NVIDIA

Chip Designer NVIDIA

Architecture Ampere

Family Jetson

Branding

Codename Hercules

Market Segment Embedded

Release Date Jan 1, 2021

Fabrication

Foundry Samsung

Fabrication Node 8N

Transistor Count 17B

Images

Used In

CPUs NVIDIAAGX Orin 64GB12 Cores

Competitors

NVIDIAGA10B 32SM vs GPU NVIDIAGA10B 28SM NVIDIAGA10B 32SM vs GPU Apple14-Core M1 Pro NVIDIAGA10B 32SM vs GPU Apple16-Core M1 Pro Show 12 more