GPU Comparison

NVIDIA

GEFORCE

NVIDIA CMP 70HX

CORE STATE GA104

VRAM 8 GB

CLOCK SPEED 1395 MHz

TDP —

BUS WIDTH 256 bit

ARCHITECTURE Ampere

nm

PROCESS 8 nm

LAUNCH DATE —

VS

NVIDIA

GEFORCE

GeForce GTX 1650

CORE STATE TU117

VRAM 4 GB

CLOCK SPEED 1665 MHz

TDP 75 W

BUS WIDTH 128 bit

ARCHITECTURE Turing

nm

PROCESS 12 nm

LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

geekbench_opencl

41,446

39,112

geekbench_vulkan

35,003

35,966

3dmark_3dmark_steel_nomad_dx12

N/A

305

passmark_directx_10

N/A

39

passmark_directx_11

N/A

58

passmark_directx_12

N/A

35

passmark_directx_9

N/A

124

passmark_g2d

N/A

561

passmark_g3d

N/A

7,880

passmark_gpu_compute

N/A

3,048

DETAILED SPECIFICATIONS

SPECIFICATION

CMP 70HX

GTX 1650

Core Specs

Shading Units

3,840

896 -76.7%

Shaders

3,840

896 -76.7%

TMUs

120

56 -53.3%

ROPs

64

32 -50.0%

SM Count

30

14 -53.3%

Clocks

Base Clock

1365 MHz

1485 MHz

Boost Clock

1395 MHz

1665 MHz

Memory Clock

1188 MHz 19 Gbps effective

2001 MHz 8 Gbps effective

Memory

Memory Size

8 GB

4 GB

VRAM (MB)

8,192

4,096 -50.0%

Memory Type

GDDR6X

GDDR5

Memory Bus

256 bit

128 bit

Bandwidth

608.3 GB/s

128.1 GB/s

Cache

L1 Cache

128 KB (per SM)

64 KB (per SM)

L2 Cache

4 MB

1024 KB

Performance

Pixel Rate

89.28 GPixel/s

53.28 GPixel/s

Texture Rate

167.4 GTexel/s

93.24 GTexel/s

FP32 (TFLOPS)

10.71 TFLOPS

2.984 TFLOPS

FP64 (TFLOPS)

167.4 GFLOPS (1:64)

93.24 GFLOPS (1:32)

FP16 (TFLOPS)

10.71 TFLOPS (1:1)

5.967 TFLOPS (2:1)

AI/RT

RT Cores

30

—

Tensor Cores

120

—

Power

TDP

—

75 W

TDP (W)

—

75

Suggested PSU

200 W

250 W

Power Connectors

1x 12-pin

None

Architecture

Architecture

Ampere

Turing

GPU Name

GA104

TU117

Generation

Mining GPUs

GeForce 16

Process Size

8 nm

12 nm

Transistors

17,400 million

4,700 million

Die Size

392 mm²

200 mm²

Foundry

Samsung

TSMC

Density

44.4M / mm²

23.5M / 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

7.5

Shader Model

6.8

6.8

Physical

Slot Width

Dual-slot

Dual-slot

Length

267 mm 10.5 inches

229 mm 9 inches

Height

112 mm 4.4 inches

111 mm 4.4 inches

Outputs

No outputs

1x DVI1x HDMI 2.01x DisplayPort 1.4a

Bus Interface

PCIe 1.0 x4

PCIe 3.0 x16

Other

Launch Price

—

149 USD

Production

End-of-life

End-of-life

Predecessor

—

GeForce 10

Successor

—

GeForce 20

View CMP 70HX Details View GeForce GTX 1650 Details