NVIDIA A40 PCIe vs Intel H3C XG310
We compared two Desktop platform GPUs: 48GB VRAM A40 PCIe and 8GB VRAM H3C XG310 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A40 PCIe 's Advantages
Boost Clock has increased by 12% (1740MHz vs 1550MHz)
More VRAM (48GB vs 8GB)
Larger VRAM bandwidth (695.8GB/s vs 68.26GB/s)
9984 additional rendering cores
Score
Benchmark
FP32 (float)
A40 PCIe
+1471%
37.42 TFLOPS
H3C XG310
2.381 TFLOPS
Graphics Card
Oct 2020
Release Date
Nov 2020
Tesla
Generation
H3C Graphics
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1305 MHz
Base Clock
900 MHz
1740 MHz
Boost Clock
1550 MHz
1812 MHz
Memory Clock
2133 MHz
Memory
48GB
Memory Size
8GB
GDDR6
Memory Type
LPDDR4X
384bit
Memory Bus
128bit
695.8GB/s
Bandwidth
68.26GB/s
Render Config
-
-
-
84
SM Count
-
10752
Shading Units
768
336
TMUs
48
112
ROPs
24
336
Tensor Cores
-
84
RT Cores
-
128 KB (per SM)
L1 Cache
-
6 MB
L2 Cache
1024 KB
-
L3 Cache
16 MB
Theoretical Performance
194.9 GPixel/s
Pixel Rate
37.20 GPixel/s
584.6 GTexel/s
Texture Rate
74.40 GTexel/s
37.42 TFLOPS
FP16 (half)
4.762 TFLOPS
37.42 TFLOPS
FP32 (float)
2.381 TFLOPS
584.6 GFLOPS
FP64 (double)
595.2 GFLOPS
Board Design
300W
TDP
300W
700 W
Suggested PSU
700 W
3x DisplayPort 1.4a
Outputs
No outputs
8-pin EPS
Power Connectors
1x 8-pin
Graphics Processor
GA102
GPU Name
DG1
-
-
-
Ampere
Architecture
Generation 12.1
Samsung
Foundry
Intel
8 nm
Process Size
10 nm
28.3 billion
Transistors
Unknown
628 mm²
Die Size
95 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
-
6.6
Shader Model
6.4
