Tesla P4 vs Radeon Instinct MI25
We compared two Professional market GPUs: 8GB VRAM Tesla P4 and 16GB VRAM Radeon Instinct MI25 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla P4 's Advantages
Lower TDP (75W vs 300W)
Radeon Instinct MI25 's Advantages
Released 9 months late
Boost Clock has increased by 35% (1500MHz vs 1114MHz)
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (436.2GB/s vs 192.3GB/s)
1536 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla P4
5704
Radeon Instinct MI25
+115%
12290
Graphics Card
Sep 2016
Release Date
Jun 2017
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
886 MHz
Base Clock
1400 MHz
1114 MHz
Boost Clock
1500 MHz
1502 MHz
Memory Clock
852 MHz
Memory
8GB
Memory Size
16GB
GDDR5
Memory Type
HBM2
256bit
Memory Bus
2048bit
192.3GB/s
Bandwidth
436.2GB/s
Render Config
-
Compute Units
64
20
SM Count
-
2560
Shading Units
4096
160
TMUs
256
64
ROPs
64
48 KB (per SM)
L1 Cache
16 KB (per CU)
2 MB
L2 Cache
4 MB
Theoretical Performance
71.30 GPixel/s
Pixel Rate
96.00 GPixel/s
178.2 GTexel/s
Texture Rate
384.0 GTexel/s
89.12 GFLOPS
FP16 (half)
24.58 TFLOPS
5.704 TFLOPS
FP32 (float)
12.29 TFLOPS
178.2 GFLOPS
FP64 (double)
768.0 GFLOPS
Board Design
75W
TDP
300W
250 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
None
Power Connectors
2x 8-pin
Graphics Processor
GP104
GPU Name
Vega 10
GP104-895-A1
GPU Variant
Vega 10 XT GL
(215-0894124)
Pascal
Architecture
GCN 5.0
TSMC
Foundry
GlobalFoundries
16 nm
Process Size
14 nm
7.2 billion
Transistors
12.5 billion
314 mm²
Die Size
495 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
6.1
CUDA
-
6.4
Shader Model
6.4
