AMD Radeon Pro Duo vs NVIDIA GRID RTX T10 8

GPU Specs Compare

Graphics Card

Release Date
Apr 2016
Unknown
Generation
Radeon Pro
GRID
Type
Desktop
Professional
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16

Clock Speeds

Memory Clock
500 MHz
1750 MHz
Base Clock
-
1065 MHz
Boost Clock
-
1395 MHz

Memory

Memory Size
4GB
8GB
Memory Type
HBM
GDDR6
Memory Bus
4096bit
384bit
Bandwidth
512.0GB/s
672.0GB/s

Render Config

Compute Units
64
-
Shading Units
4096
3584
TMUs
256
224
ROPs
64
64
L1 Cache
16 KB (per CU)
64 KB (per SM)
L2 Cache
2 MB
6 MB
SM Count
-
56
Tensor Cores
-
448
RT Cores
-
56

Theoretical Performance

Pixel Rate
64.00 GPixel/s
89.28 GPixel/s
Texture Rate
256.0 GTexel/s
312.5 GTexel/s
FP16 (half)
8.192 TFLOPS
20.00 TFLOPS
FP32 (float)
8.192 TFLOPS
9.999 TFLOPS
FP64 (double)
512.0 GFLOPS
312.5 GFLOPS

Graphics Processor

GPU Name
Capsaicin
TU102
GPU Variant
Capsaicin XT
TU102-875-A1
Architecture
GCN 3.0
Turing
Foundry
TSMC
TSMC
Process Size
28 nm
12 nm
Transistors
8.9 billion
18.6 billion
Die Size
596 mm²
754 mm²

Board Design

TDP
350W
150W
Suggested PSU
750 W
450 W
Outputs
1x HDMI 1.4a3x DisplayPort 1.2
No outputs
Power Connectors
3x 8-pin
1x 6-pin + 1x 8-pin

Graphics Features

DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.0
3.0
Vulkan
1.2
1.3
Shader Model
6.0
6.8
CUDA
-
7.5