NVIDIA A40 Full Specs - HMC

10,752 Shaders

1.74GHz

48GB GDDR6347.9GB/s

··

37.42 TFLOPS

Form Factor

PCIe Card

TDP

300W

Power Connectors

1x 8-Pin EPS

A40

A401.2 POPSINT4 Tensor Sparse

x1

3.35 PFLOPS FP4 Tensor SparseGeForce RTX 5090

x2.80

Clock Speed

···

Peak OPS

1.2 POPSINT4 Tensor Sparse

Tensor FP16-16

149.7 TFLOPS

FP16-16 Tensor Sparse

299.3 TFLOPS

Tensor FP16-32

74.83 TFLOPS

FP16-32 Tensor Sparse

149.7 TFLOPS

BF16

37.42 TFLOPS

Tensor BF16

74.83 TFLOPS

BF16 Tensor Sparse

149.7 TFLOPS

Tensor TF32

37.42 TFLOPS

FP32

37.42 TFLOPS

FP64

584.6 GFLOPS

Tensor INT4

598.7 TOPS

Tensor INT8

299.3 TOPS

Ray

56.43 TOPS

Pixel Rate

194.9 GPixel/s

Texture Rate

584.6 GTexel/s

Shaders

10,752 Shaders

TMUs

336 TMUs

ROPs

112 ROPs

Tensor Cores

336 T-Cores

RT Cores

84 RT-Cores

SMs

84 SMs

Base Clock

1.3GHz

Boost Clock

1.74GHz

L1

64KB/SM Tex

L2 Cache

6MB shared

48GB GDDR6

Memory Bus

384-bit

Memory Speed

7.2GT/s

Memory Bandwidth

347.9GB/s

ECC

No

TDP

300W

Max Resolution

7680x4320

Refresh Rate Calculator

7680x4320

Resolution8K UHD

Refresh Rate

60Hz

Multi-Monitor

3

Adaptive Sync

G-Sync

FreeSync

DSC

Supported

HDCP

HDCP 2.3

3x DisplayPort 1.3

Shader Model

6.6

DirectX

DirectX 12

Direct3D

12_2

OpenGL

4.6

OpenCL

3

Vulkan

1.2

CUDA

8.6

PureVideo HD

VP11

VDPAU

Feature Set K

Encoder

NVENC 7

Codec

AVC (H.264)

HEVC (H.265)

Decoder

NVDEC 5

Codec

MPEG-1

MPEG-2

MPEG-4

VC-1

VP8

VP9

AVC (H.264)

HEVC (H.265)

AV1

Form Factor

PCIe Card

PCIe

PCIe 4.0 x16

2-Slots

Height

112mm (4.41")

Width

267mm (10.51")

Depth

40mm (1.57")

Cooling

Passive

Power Connectors

1x 8-Pin EPS

Manufacturer

Chip Designer

Architecture

Family

Branding

Codename

NV172

Chip Variant

GA102-200-KD-A1

Market Segment

Server

Release Date

Oct 5, 2020

Foundry

Samsung

Fabrication Node

8N

Die Size

628mm²

Transistor Count

28.3B

Transistor Density

45.04 MTr/mm²