NVIDIA B100 vs Intel Arc A380
We compared two Desktop platform GPUs: 96GB VRAM B100 and 6GB VRAM Arc A380 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B100 's Advantages
Released 2 years and 5 months late
More VRAM (96GB vs 6GB)
Larger VRAM bandwidth (4.10TB/s vs 186.0GB/s)
15872 additional rendering cores
Intel Arc A380 's Advantages
Boost Clock has increased by 12% (2050MHz vs 1837MHz)
Lower TDP (75W vs 1000W)
Score
Benchmark
FP32 (float)
B100
+1378%
62.08 TFLOPS
Arc A380
4.198 TFLOPS
Graphics Card
Nov 2024
Release Date
Jun 2022
Server Blackwell
Generation
Alchemist(Arc 3)
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
1665 MHz
Base Clock
2000 MHz
1837 MHz
Boost Clock
2050 MHz
2000 MHz
Memory Clock
1937 MHz
Memory
96GB
Memory Size
6GB
HBM3e
Memory Type
GDDR6
4096bit
Memory Bus
96bit
4.10TB/s
Bandwidth
186.0GB/s
Render Config
-
-
-
132
SM Count
-
16896
Shading Units
1024
528
TMUs
64
24
ROPs
32
528
Tensor Cores
128
-
RT Cores
8
256 KB (per SM)
L1 Cache
-
50 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
44.09 GPixel/s
Pixel Rate
65.60 GPixel/s
969.9 GTexel/s
Texture Rate
131.2 GTexel/s
248.3 TFLOPS
FP16 (half)
8.397 TFLOPS
62.08 TFLOPS
FP32 (float)
4.198 TFLOPS
31.04 TFLOPS
FP64 (double)
1050 GFLOPS
Board Design
1000W
TDP
75W
1400 W
Suggested PSU
250 W
No outputs
Outputs
1x HDMI 2.13x DisplayPort 2.0
-
Power Connectors
1x 8-pin
Graphics Processor
GB102
GPU Name
DG2-128
-
GPU Variant
ACM-G11
Blackwell
Architecture
Generation 12.7
TSMC
Foundry
TSMC
5 nm
Process Size
6 nm
104 billion
Transistors
7.2 billion
Unknown
Die Size
157 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
10.1
CUDA
-
N/A
Shader Model
6.6
