Quadro RTX 8000 vs Tesla V100 DGXS 16 GB
We compared two Professional market GPUs: 48GB VRAM Quadro RTX 8000 and 16GB VRAM Tesla V100 DGXS 16 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Quadro RTX 8000 's Advantages
Boost Clock has increased by 16% (1770MHz vs 1530MHz)
More VRAM (48GB vs 16GB)
Tesla V100 DGXS 16 GB 's Advantages
Larger VRAM bandwidth (897.0GB/s vs 672.0GB/s)
512 additional rendering cores
Lower TDP (250W vs 260W)
Score
Benchmark
FP32 (float)
Quadro RTX 8000
+4%
16310
Tesla V100 DGXS 16 GB
15670
Graphics Card
Aug 2018
Release Date
Mar 2018
Quadro
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1395 MHz
Base Clock
1327 MHz
1770 MHz
Boost Clock
1530 MHz
1750 MHz
Memory Clock
876 MHz
Memory
48GB
Memory Size
16GB
GDDR6
Memory Type
HBM2
384bit
Memory Bus
4096bit
672.0GB/s
Bandwidth
897.0GB/s
Render Config
72
SM Count
80
4608
Shading Units
5120
288
TMUs
320
96
ROPs
128
576
Tensor Cores
640
72
RT Cores
-
64 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
6 MB
Theoretical Performance
169.9 GPixel/s
Pixel Rate
195.8 GPixel/s
509.8 GTexel/s
Texture Rate
489.6 GTexel/s
32.62 TFLOPS
FP16 (half)
31.33 TFLOPS
16.31 TFLOPS
FP32 (float)
15.67 TFLOPS
509.8 GFLOPS
FP64 (double)
7.834 TFLOPS
Board Design
260W
TDP
250W
600 W
Suggested PSU
600 W
4x DisplayPort 1.4a
1x USB Type-C
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
TU102
GPU Name
GV100
TU102-875-A1
GPU Variant
-
Turing
Architecture
Volta
TSMC
Foundry
TSMC
12 nm
Process Size
12 nm
18.6 billion
Transistors
21.1 billion
754 mm²
Die Size
815 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
7.5
CUDA
7.0
6.6
Shader Model
6.6
