NVIDIA CMP 50HX vs NVIDIA CMP 70HX

Edit	NVIDIA CMP 50HX Check Price	NVIDIA CMP 70HX Check Price

Table of Contents

Graphics Processor
Graphics Card
Clocks
Memory Configuration
Render Configuration
Performance
Dimensions & Outputs
API Support & Features
Other Features

Graphics Processor

GPU model	TU102	GA104
GPU variant	TU102-100-A1	GA104-100-A1
Architecture	Turing	Ampere
Foundry	TSMC	Samsung
Manufacturing process	12 nm	8 nm
Number of transistors	18,600 million	17,400 million
Die size	754 mm²	392 mm²

Graphics Card

Release date	Jun 24th, 2021	Unknown
Generation	Mining GPUs	Mining GPUs
Production	Active	Active
Interface	PCIe 3.0 x16	PCIe 4.0 x16

Clocks

Base clock	1350 MHz	1365 MHz
Boost clock	1545 MHz	1395 MHz
Memory clock	1750 MHz 14 Gbps effective	1188 MHz 19 Gbps effective

Memory Configuration

Memory size	10 GB	8 GB
Memory type	GDDR6	GDDR6X
Memory bus width	320 bit	256 bit
Bandwidth	560.0 GB/s	608.3 GB/s

Render Configuration

Shading units	3584	6144
TMUs	192	192
ROPs	80	96
SM count	56	48
Tensor cores	448	192
RT cores	56	48
Cache L1	64 KB (per SM)	128 KB (per SM)
Cache L2	5 MB	4 MB

Performance

Pixel rate	123.6 GPixel/s	133.9 GPixel/s
Texture rate	296.6 GTexel/s	267.8 GTexel/s
FP16 (half) performance	22.15 TFLOPS (2:1)	17.14 TFLOPS (1:1)
FP32 (float) performance	11.07 TFLOPS	17.14 TFLOPS
FP64 (double) performance	346.1 GFLOPS (1:32)	267.8 GFLOPS (1:64)

Dimensions & Outputs

Slot width	Dual-slot	Dual-slot
Length	267 mm 10.5 inches	267 mm 10.5 inches
Width	116 mm 4.6 inches	112 mm 4.4 inches
Height	35 mm 1.4 inches	—
TDP	250 W	unknown
Suggested PSU	600 W	200 W
Outputs	No outputs	No outputs
Power connectors	2x 8-pin	1x 12-pin
Board number	PG150 SKU 100	—

API Support & Features

DirectX	12 Ultimate (12_2)	12 Ultimate (12_2)
OpenGL	4.6	4.6
OpenCL	3.0	3.0
Vulkan	1.2	1.2
CUDA	7.5	8.6
Shader model	6.6	6.6

Other Features

Compare