Home GPU Comparison NVIDIA CMP 40HX vs AMD Radeon HD 8990 OEM

NVIDIA CMP 40HX vs AMD Radeon HD 8990 OEM

We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 3GB VRAM Radeon HD 8990 OEM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA CMP 40HX 's Advantages
Released 7 years and 10 months late
Boost Clock has increased by 65% (1650MHz vs 1000MHz)
More VRAM (8GB vs 3GB)
Larger VRAM bandwidth (448.0GB/s vs 288.0GB/s)
256 additional rendering cores
Lower TDP (185W vs 375W)

Score

Benchmark

FP32 (float)
CMP 40HX +85%
7.603 TFLOPS
Radeon HD 8990 OEM
4.096 TFLOPS
VS

Graphics Card

Feb 2021
Release Date
Apr 2013
Mining GPUs
Generation
Sea Islands
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16

Clock Speeds

1470 MHz
Base Clock
950 MHz
1650 MHz
Boost Clock
1000 MHz
1750 MHz
Memory Clock
1500 MHz

Memory

8GB
Memory Size
3GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
384bit
448.0GB/s
Bandwidth
288.0GB/s

Render Config

-
Compute Units
32
36
SM Count
-
2304
Shading Units
2048
144
TMUs
128
64
ROPs
32
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
768 KB
-
-
-

Theoretical Performance

105.6 GPixel/s
Pixel Rate
32.00 GPixel/s
237.6 GTexel/s
Texture Rate
128.0 GTexel/s
15.21 TFLOPS
FP16 (half)
-
7.603 TFLOPS
FP32 (float)
4.096 TFLOPS
237.6 GFLOPS
FP64 (double)
1024 GFLOPS

Board Design

185W
TDP
375W
450 W
Suggested PSU
750 W
No outputs
Outputs
1x DVI 4x mini-DisplayPort 1.2
1x 8-pin
Power Connectors
2x 8-pin

Graphics Processor

TU106
GPU Name
Malta
TU106-100-A1
GPU Variant
Malta XT (215-0849026)
Turing
Architecture
GCN 1.0
TSMC
Foundry
TSMC
12 nm
Process Size
28 nm
10.8 billion
Transistors
4.313 billion
445 mm²
Die Size
365 mm²

Graphics Features

12 Ultimate (12_2)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
1.2
1.3
Vulkan
1.2
7.5
CUDA
-
6.6
Shader Model
5.1

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy