Home GPU Comparison AMD Radeon HD 7990 vs NVIDIA A40 PCIe

AMD Radeon HD 7990 vs NVIDIA A40 PCIe

We compared two Desktop platform GPUs: 3GB VRAM Radeon HD 7990 and 48GB VRAM A40 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA A40 PCIe 's Advantages
Released 7 years and 6 months late
Boost Clock has increased by 74% (1740MHz vs 1000MHz)
More VRAM (48GB vs 3GB)
Larger VRAM bandwidth (695.8GB/s vs 288.0GB/s)
8704 additional rendering cores
Lower TDP (300W vs 375W)

Score

Benchmark

FP32 (float)
Radeon HD 7990
4.096 TFLOPS
A40 PCIe +813%
37.42 TFLOPS
VS

Graphics Card

Apr 2013
Release Date
Oct 2020
Southern Islands
Generation
Tesla
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

950 MHz
Base Clock
1305 MHz
1000 MHz
Boost Clock
1740 MHz
1500 MHz
Memory Clock
1812 MHz

Memory

3GB
Memory Size
48GB
GDDR5
Memory Type
GDDR6
384bit
Memory Bus
384bit
288.0GB/s
Bandwidth
695.8GB/s

Render Config

32
Compute Units
-
-
SM Count
84
2048
Shading Units
10752
128
TMUs
336
32
ROPs
112
-
Tensor Cores
336
-
RT Cores
84
16 KB (per CU)
L1 Cache
128 KB (per SM)
768 KB
L2 Cache
6 MB
-
-
-

Theoretical Performance

32.00 GPixel/s
Pixel Rate
194.9 GPixel/s
128.0 GTexel/s
Texture Rate
584.6 GTexel/s
-
FP16 (half)
37.42 TFLOPS
4.096 TFLOPS
FP32 (float)
37.42 TFLOPS
1024 GFLOPS
FP64 (double)
584.6 GFLOPS

Board Design

375W
TDP
300W
750 W
Suggested PSU
700 W
1x DVI 4x mini-DisplayPort 1.2
Outputs
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
8-pin EPS

Graphics Processor

Malta
GPU Name
GA102
Malta XT (215-0849026)
GPU Variant
-
GCN 1.0
Architecture
Ampere
TSMC
Foundry
Samsung
28 nm
Process Size
8 nm
4.313 billion
Transistors
28.3 billion
365 mm²
Die Size
628 mm²

Graphics Features

12 (11_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
1.2
OpenCL
3.0
1.2
Vulkan
1.3
-
CUDA
8.6
5.1
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy