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

Quadro GV100

CORE STATE GV100

VRAM 32 GB

CLOCK SPEED 1627 MHz

TDP 250 W

BUS WIDTH 4096 bit

ARCHITECTURE Volta

nm

PROCESS 12 nm

LAUNCH DATE 2018

PERFORMANCE BENCHMARKS

geekbench_opencl

135,230

144,393

geekbench_vulkan

N/A

137,547

passmark_directx_10

N/A

140

passmark_directx_11

N/A

168

passmark_directx_12

N/A

84

passmark_directx_9

N/A

207

passmark_g2d

N/A

836

passmark_g3d

N/A

19,650

passmark_gpu_compute

N/A

9,069

DETAILED SPECIFICATIONS

SPECIFICATION

A10M

Quadro GV100

Core Specs

Shading Units

7,168

5,120 -28.6%

Shaders

7,168

5,120 -28.6%

TMUs

224

320 +42.9%

ROPs

80

128 +60.0%

SM Count

56

80 +42.9%

Clocks

Base Clock

975 MHz

1132 MHz

Boost Clock

1635 MHz

1627 MHz

Memory Clock

1563 MHz 12.5 Gbps effective

848 MHz 1696 Mbps effective

Memory

Memory Size

20 GB

32 GB

VRAM (MB)

20,480

32,768 +60.0%

Memory Type

GDDR6

HBM2

Memory Bus

320 bit

4096 bit

Bandwidth

500.2 GB/s

868.4 GB/s

Cache

L1 Cache

128 KB (per SM)

128 KB (per SM)

L2 Cache

6 MB

6 MB

Performance

Pixel Rate

130.8 GPixel/s

208.3 GPixel/s

Texture Rate

366.2 GTexel/s

520.6 GTexel/s

FP32 (TFLOPS)

23.44 TFLOPS

16.66 TFLOPS

FP64 (TFLOPS)

732.5 GFLOPS (1:32)

8.330 TFLOPS (1:2)

FP16 (TFLOPS)

23.44 TFLOPS (1:1)

33.32 TFLOPS (2:1)

AI/RT

RT Cores

56

—

Tensor Cores

224

640 +185.7%

Power

TDP

150 W

250 W

TDP (W)

150

250 +66.7%

Suggested PSU

450 W

600 W

Power Connectors

8-pin EPS

1x 8-pin

Architecture

Architecture

Ampere

Volta

GPU Name

GA102

GV100

Generation

Server Ampere (Axx)

Quadro Volta (Vx000)

Process Size

8 nm

12 nm

Transistors

28,300 million

21,100 million

Die Size

628 mm²

815 mm²

Foundry

Samsung

TSMC

Density

45.1M / mm²

25.9M / 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

7.0

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

4x DisplayPort 1.4a

Bus Interface

PCIe 4.0 x16

PCIe 3.0 x16

Other

Launch Price

—

8,999 USD

Production

End-of-life

End-of-life

Predecessor

Tesla Turing

Quadro Pascal

Successor

Server Ada

Quadro Turing

View A10M Details View Quadro GV100 Details