NVIDIA Tesla V100 PCIe 32 GB vs AMD Radeon Instinct MI6
We compared two Professional market GPUs: 32GB VRAM Tesla V100 PCIe 32 GB and 8GB VRAM Radeon Instinct MI6 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla V100 PCIe 32 GB 's Advantages
Released 1 years and 3 months late
Boost Clock has increased by 12% (1380MHz vs 1233MHz)
More VRAM (32GB vs 8GB)
Larger VRAM bandwidth (897.0GB/s vs 224.0GB/s)
2816 additional rendering cores
AMD Radeon Instinct MI6 's Advantages
Lower TDP (150W vs 250W)
Score
Benchmark
FP32 (float)
Tesla V100 PCIe 32 GB
+148%
14.13 TFLOPS
Radeon Instinct MI6
5.682 TFLOPS
Graphics Card
Mar 2018
Release Date
Dec 2016
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1230 MHz
Base Clock
1120 MHz
1380 MHz
Boost Clock
1233 MHz
876 MHz
Memory Clock
1750 MHz
Memory
32GB
Memory Size
8GB
HBM2
Memory Type
GDDR5
4096bit
Memory Bus
256bit
897.0GB/s
Bandwidth
224.0GB/s
Render Config
-
Compute Units
36
80
SM Count
-
5120
Shading Units
2304
320
TMUs
144
128
ROPs
32
640
Tensor Cores
-
-
-
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
6 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
176.6 GPixel/s
Pixel Rate
39.46 GPixel/s
441.6 GTexel/s
Texture Rate
177.6 GTexel/s
28.26 TFLOPS
FP16 (half)
5.682 TFLOPS
14.13 TFLOPS
FP32 (float)
5.682 TFLOPS
7.066 TFLOPS
FP64 (double)
355.1 GFLOPS
Board Design
250W
TDP
150W
600 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
GV100
GPU Name
Ellesmere
-
GPU Variant
Ellesmere XT
Volta
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
12 nm
Process Size
14 nm
21.1 billion
Transistors
5.7 billion
815 mm²
Die Size
232 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
7.0
CUDA
-
6.6
Shader Model
6.4
