AMD Radeon Instinct MI8 vs NVIDIA Tesla T10
We compared two Professional market GPUs: 4GB VRAM Radeon Instinct MI8 and 24GB VRAM Tesla T10 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI8 's Advantages
Lower TDP (175W vs 260W)
NVIDIA Tesla T10 's Advantages
Boost Clock1560MHz
More VRAM (24GB vs 4GB)
Larger VRAM bandwidth (624.0GB/s vs 512.0GB/s)
512 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Instinct MI8
8.192 TFLOPS
Tesla T10
+75%
14.38 TFLOPS
Graphics Card
Dec 2016
Release Date
Unknown
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
1305 MHz
-
Boost Clock
1560 MHz
500 MHz
Memory Clock
1625 MHz
Memory
4GB
Memory Size
24GB
HBM
Memory Type
GDDR6
4096bit
Memory Bus
384bit
512.0GB/s
Bandwidth
624.0GB/s
Render Config
64
Compute Units
-
-
SM Count
72
4096
Shading Units
4608
256
TMUs
288
64
ROPs
96
-
Tensor Cores
576
-
RT Cores
72
16 KB (per CU)
L1 Cache
64 KB (per SM)
2 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
149.8 GPixel/s
256.0 GTexel/s
Texture Rate
449.3 GTexel/s
8.192 TFLOPS
FP16 (half)
28.75 TFLOPS
8.192 TFLOPS
FP32 (float)
14.38 TFLOPS
512.0 GFLOPS
FP64 (double)
449.3 GFLOPS
Board Design
175W
TDP
260W
450 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
Fiji
GPU Name
TU102
Fiji XT CA
(215-0862120)
GPU Variant
-
GCN 3.0
Architecture
Turing
TSMC
Foundry
TSMC
28 nm
Process Size
12 nm
8.9 billion
Transistors
18.6 billion
596 mm²
Die Size
754 mm²
Graphics Features
12 (12_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2.170
Vulkan
1.3
-
CUDA
7.5
6.5
Shader Model
6.6
