Tesla V100 PCIe 16 GB vs Tesla V100 FHHL
We compared two Professional market GPUs: 16GB VRAM Tesla V100 PCIe 16 GB and 16GB VRAM Tesla V100 FHHL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla V100 PCIe 16 GB Advantages
Boost Clock has increased by 7% (1380MHz vs 1290MHz)
Larger VRAM bandwidth (897.0GB/s vs 829.4GB/s)
Tesla V100 FHHL Advantages
Released 9 months late
Lower TDP (250W vs 300W)
Score
Benchmark
FP32 (float)
Tesla V100 PCIe 16 GB
+6%
14130
Tesla V100 FHHL
13210
Graphics Card
Jun 2017
Release Date
Mar 2018
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1245 MHz
Base Clock
937 MHz
1380 MHz
Boost Clock
1290 MHz
876 MHz
Memory Clock
810 MHz
Memory
16GB
Memory Size
16GB
HBM2
Memory Type
HBM2
4096bit
Memory Bus
4096bit
897.0GB/s
Bandwidth
829.4GB/s
Render Config
80
SM Count
80
5120
Shading Units
5120
320
TMUs
320
128
ROPs
128
640
Tensor Cores
640
128 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
6 MB
Theoretical Performance
176.6 GPixel/s
Pixel Rate
165.1 GPixel/s
441.6 GTexel/s
Texture Rate
412.8 GTexel/s
28.26 TFLOPS
FP16 (half)
26.42 TFLOPS
14.13 TFLOPS
FP32 (float)
13.21 TFLOPS
7.066 TFLOPS
FP64 (double)
6.605 TFLOPS
Board Design
300W
TDP
250W
700 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
GV100
GPU Name
GV100
Volta
Architecture
Volta
TSMC
Foundry
TSMC
12 nm
Process Size
12 nm
21.1 billion
Transistors
21.1 billion
815 mm²
Die Size
815 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.0
CUDA
7.0
6.6
Shader Model
6.6
