AMD Radeon Pro Duo vs NVIDIA GRID M10 8Q

GPU · Specs Compare

Products
GPU AMD Radeon Pro Duo AMD · 2016-04
GPU NVIDIA GRID M10 8Q NVIDIA · 2016-05
Graphics Card
Release Date
Apr 2016
May 2016
Generation
Radeon Pro
GRID
Type
Desktop
Professional
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Clock Speeds
Memory Clock
500 MHz
1300 MHz
Base Clock
—
1033 MHz
Boost Clock
—
1306 MHz
Memory
Memory Size
4GB
8GB
Memory Type
HBM
GDDR5
Memory Bus
4096bit
128bit
Bandwidth
512.0GB/s
83.20GB/s
Render Config
Compute Units
64
—
Shading Units
4096
640
TMUs
256
40
ROPs
64
16
L1 Cache
16 KB (per CU)
64 KB (per SMM)
L2 Cache
2 MB
2 MB
Theoretical Performance
Pixel Rate
64.00 GPixel/s
20.90 GPixel/s
Texture Rate
256.0 GTexel/s
52.24 GTexel/s
FP16 (half)
8.192 TFLOPS
—
FP32 (float)
8.192 TFLOPS
1.672 TFLOPS
FP64 (double)
512.0 GFLOPS
52.24 GFLOPS
Graphics Processor
GPU Name
Capsaicin
GM107
GPU Variant
Capsaicin XT
GM107-570-A2
Architecture
GCN 3.0
Maxwell
Foundry
TSMC
TSMC
Process Size
28 nm
28 nm
Transistors
8.9 billion
1.87 billion
Die Size
596 mm²
148 mm²
Board Design
TDP
350W
225W
Suggested PSU
750 W
550 W
Outputs
1x HDMI 1.4a3x DisplayPort 1.2
No outputs
Power Connectors
3x 8-pin
1x 8-pin
Graphics Features
DirectX
12 (12_0)
12 (11_0)
OpenGL
4.6
4.6
OpenCL
2.0
3.0
Vulkan
1.2
1.3
Shader Model
6.0
5.1
CUDA
—
5.0
▲ Specs Compare Data sourced from official specifications and benchmark tests.