Intel H3C XG310 vs NVIDIA B100
We compared two Desktop platform GPUs: 8GB VRAM H3C XG310 and 96GB VRAM B100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel H3C XG310 's Advantages
Lower TDP (300W vs 1000W)
NVIDIA B100 's Advantages
Released 4 years late
Boost Clock has increased by 19% (1837MHz vs 1550MHz)
More VRAM (96GB vs 8GB)
Larger VRAM bandwidth (4.10TB/s vs 68.26GB/s)
16128 additional rendering cores
Score
Benchmark
FP32 (float)
H3C XG310
2.381 TFLOPS
B100
+2507%
62.08 TFLOPS
Graphics Card
Nov 2020
Release Date
Nov 2024
H3C Graphics
Generation
Server Blackwell
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
900 MHz
Base Clock
1665 MHz
1550 MHz
Boost Clock
1837 MHz
2133 MHz
Memory Clock
2000 MHz
Memory
8GB
Memory Size
96GB
LPDDR4X
Memory Type
HBM3e
128bit
Memory Bus
4096bit
68.26GB/s
Bandwidth
4.10TB/s
Render Config
-
-
-
-
SM Count
132
768
Shading Units
16896
48
TMUs
528
24
ROPs
24
-
Tensor Cores
528
-
-
-
-
L1 Cache
256 KB (per SM)
1024 KB
L2 Cache
50 MB
16 MB
L3 Cache
-
Theoretical Performance
37.20 GPixel/s
Pixel Rate
44.09 GPixel/s
74.40 GTexel/s
Texture Rate
969.9 GTexel/s
4.762 TFLOPS
FP16 (half)
248.3 TFLOPS
2.381 TFLOPS
FP32 (float)
62.08 TFLOPS
595.2 GFLOPS
FP64 (double)
31.04 TFLOPS
Board Design
300W
TDP
1000W
700 W
Suggested PSU
1400 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
-
Graphics Processor
DG1
GPU Name
GB102
-
-
-
Generation 12.1
Architecture
Blackwell
Intel
Foundry
TSMC
10 nm
Process Size
5 nm
Unknown
Transistors
104 billion
95 mm²
Die Size
Unknown
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
-
CUDA
10.1
6.4
Shader Model
N/A
