AMD FireStream 9370 vs NVIDIA A40 PCIe
We compared two Desktop platform GPUs: 4GB VRAM FireStream 9370 and 48GB VRAM A40 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD FireStream 9370 's Advantages
Lower TDP (225W vs 300W)
NVIDIA A40 PCIe 's Advantages
Released 10 years and 4 months late
Boost Clock1740MHz
More VRAM (48GB vs 4GB)
Larger VRAM bandwidth (695.8GB/s vs 147.2GB/s)
9152 additional rendering cores
Score
Benchmark
FP32 (float)
FireStream 9370
2.64 TFLOPS
A40 PCIe
+1317%
37.42 TFLOPS
Graphics Card
Jun 2010
Release Date
Oct 2020
FireStream
Generation
Tesla
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1305 MHz
-
Boost Clock
1740 MHz
1150 MHz
Memory Clock
1812 MHz
Memory
4GB
Memory Size
48GB
GDDR5
Memory Type
GDDR6
256bit
Memory Bus
384bit
147.2GB/s
Bandwidth
695.8GB/s
Render Config
20
Compute Units
-
-
SM Count
84
1600
Shading Units
10752
80
TMUs
336
32
ROPs
112
-
Tensor Cores
336
-
RT Cores
84
8 KB (per CU)
L1 Cache
128 KB (per SM)
512 KB
L2 Cache
6 MB
-
-
-
Theoretical Performance
26.40 GPixel/s
Pixel Rate
194.9 GPixel/s
66.00 GTexel/s
Texture Rate
584.6 GTexel/s
-
FP16 (half)
37.42 TFLOPS
2.640 TFLOPS
FP32 (float)
37.42 TFLOPS
528.0 GFLOPS
FP64 (double)
584.6 GFLOPS
Board Design
225W
TDP
300W
550 W
Suggested PSU
700 W
1x DisplayPort 1.1
Outputs
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
Cypress
GPU Name
GA102
Cypress XT GL
GPU Variant
-
TeraScale 2
Architecture
Ampere
TSMC
Foundry
Samsung
40 nm
Process Size
8 nm
2.154 billion
Transistors
28.3 billion
334 mm²
Die Size
628 mm²
Graphics Features
11.2 (11_0)
DirectX
12 Ultimate (12_2)
4.4
OpenGL
4.6
1.2
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
8.6
5.0
Shader Model
6.6
