GPU Comparison

NVIDIA

GEFORCE

NVIDIA A10M

CORE STATE GA102

VRAM 20 GB

CLOCK SPEED 1635 MHz

TDP 150 W

BUS WIDTH 320 bit

ARCHITECTURE Ampere

nm

PROCESS 8 nm

LAUNCH DATE —

VS

NVIDIA

GEFORCE

GeForce GTX 970

CORE STATE GM204

VRAM 4 GB

CLOCK SPEED 1178 MHz

TDP 148 W

BUS WIDTH 256 bit

ARCHITECTURE Maxwell 2.0

nm

PROCESS 28 nm

LAUNCH DATE 2014

PERFORMANCE BENCHMARKS

geekbench_opencl

135,230

28,528

3dmark_3dmark_steel_nomad_dx12

N/A

369

geekbench_metal

N/A

13,595

geekbench_vulkan

N/A

31,001

passmark_directx_10

N/A

46

passmark_directx_11

N/A

71

passmark_directx_12

N/A

41

passmark_directx_9

N/A

143

passmark_g2d

N/A

764

passmark_g3d

N/A

9,638

passmark_gpu_compute

N/A

4,073

DETAILED SPECIFICATIONS

SPECIFICATION

A10M

GTX 970

Core Specs

Shading Units

7,168

1,664 -76.8%

Shaders

7,168

1,664 -76.8%

TMUs

224

104 -53.6%

ROPs

80

56 -30.0%

SM Count

56

—

Clocks

Base Clock

975 MHz

1050 MHz

Boost Clock

1635 MHz

1178 MHz

Memory Clock

1563 MHz 12.5 Gbps effective

1753 MHz 7 Gbps effective

Memory

Memory Size

20 GB

4 GB

VRAM (MB)

20,480

4,096 -80.0%

Memory Type

GDDR6

GDDR5

Memory Bus

320 bit

256 bit

Bandwidth

500.2 GB/s

224.4 GB/s

Cache

L1 Cache

128 KB (per SM)

48 KB (per SMM)

L2 Cache

6 MB

2 MB

Performance

Pixel Rate

130.8 GPixel/s

65.97 GPixel/s

Texture Rate

366.2 GTexel/s

122.5 GTexel/s

FP32 (TFLOPS)

23.44 TFLOPS

3.920 TFLOPS

FP64 (TFLOPS)

732.5 GFLOPS (1:32)

122.5 GFLOPS (1:32)

FP16 (TFLOPS)

23.44 TFLOPS (1:1)

—

AI/RT

RT Cores

56

—

Tensor Cores

224

—

Power

TDP

150 W

148 W

TDP (W)

150

148 -1.3%

Suggested PSU

450 W

300 W

Power Connectors

8-pin EPS

2x 6-pin

Architecture

Architecture

Ampere

Maxwell 2.0

GPU Name

GA102

GM204

Generation

Server Ampere (Axx)

GeForce 900

Process Size

8 nm

28 nm

Transistors

28,300 million

5,200 million

Die Size

628 mm²

398 mm²

Foundry

Samsung

TSMC

Density

45.1M / mm²

13.1M / mm²

API Support

DirectX

12 Ultimate (12_2)

12 (12_1)

OpenGL

4.6

4.6

Vulkan

1.4

1.4

OpenCL

3.0

3.0

CUDA

8.6

5.2

Shader Model

6.8

6.8

Physical

Slot Width

Single-slot

Dual-slot

Length

267 mm 10.5 inches

267 mm 10.5 inches

Height

112 mm 4.4 inches

111 mm 4.4 inches

Outputs

No outputs

1x DVI1x HDMI 2.03x DisplayPort 1.2

Bus Interface

PCIe 4.0 x16

PCIe 3.0 x16

Other

Launch Price

—

329 USD

Production

End-of-life

End-of-life

Predecessor

Tesla Turing

GeForce 700

Successor

Server Ada

GeForce 10

View A10M Details View GeForce GTX 970 Details