Intel Data Center GPU Max 1350 vs NVIDIA Tesla P4
We compared two Professional market GPUs: 96GB VRAM Data Center GPU Max 1350 and 8GB VRAM Tesla P4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Data Center GPU Max 1350 's Advantages
Released 6 years and 4 months late
Boost Clock has increased by 39% (1550MHz vs 1114MHz)
More VRAM (96GB vs 8GB)
Larger VRAM bandwidth (2458GB/s vs 192.3GB/s)
11776 additional rendering cores
NVIDIA Tesla P4 's Advantages
Lower TDP (75W vs 450W)
Score
Benchmark
FP32 (float)
Data Center GPU Max 1350
+679%
44.44 TFLOPS
Tesla P4
5.704 TFLOPS
Graphics Card
Jan 2023
Release Date
Sep 2016
Data Center GPU
Generation
Tesla
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
750 MHz
Base Clock
886 MHz
1550 MHz
Boost Clock
1114 MHz
1200 MHz
Memory Clock
1502 MHz
Memory
96GB
Memory Size
8GB
HBM2e
Memory Type
GDDR5
8192bit
Memory Bus
256bit
2458GB/s
Bandwidth
192.3GB/s
Render Config
-
-
-
-
SM Count
20
14336
Shading Units
2560
896
TMUs
160
0
ROPs
64
896
Tensor Cores
-
112
RT Cores
-
64 KB (per EU)
L1 Cache
48 KB (per SM)
408 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
71.30 GPixel/s
1389 GTexel/s
Texture Rate
178.2 GTexel/s
44.44 TFLOPS
FP16 (half)
89.12 GFLOPS
44.44 TFLOPS
FP32 (float)
5.704 TFLOPS
44.44 TFLOPS
FP64 (double)
178.2 GFLOPS
Board Design
450W
TDP
75W
850 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
-
Power Connectors
None
Graphics Processor
Ponte Vecchio
GPU Name
GP104
-
GPU Variant
GP104-895-A1
Generation 12.5
Architecture
Pascal
Intel
Foundry
TSMC
10 nm
Process Size
16 nm
100 billion
Transistors
7.2 billion
1280 mm²
Die Size
314 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
6.1
6.6
Shader Model
6.4
