GPU Comparison
GEFORCE
NVIDIA P102-100
CORE STATE
GP102
VRAM
5 GB
CLOCK SPEED
1683 MHz
TDP
250 W
BUS WIDTH
320 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2018
VS
GEFORCE
Tesla P4
CORE STATE
GP104
VRAM
8 GB
CLOCK SPEED
1114 MHz
TDP
75 W
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
P102-100
Tesla P4
Core Specs
Shading Units
3,200
2,560
-20.0%
Shaders
3,200
2,560
-20.0%
TMUs
200
160
-20.0%
ROPs
80
64
-20.0%
SM Count
25
20
-20.0%
Clocks
Base Clock
1582 MHz
886 MHz
Boost Clock
1683 MHz
1114 MHz
Memory Clock
1376 MHz
11 Gbps effective
1502 MHz
6 Gbps effective
Memory
Memory Size
5 GB
8 GB
VRAM (MB)
5,120
8,192
+60.0%
Memory Type
GDDR5X
GDDR5
Memory Bus
320 bit
256 bit
Bandwidth
440.3 GB/s
192.3 GB/s
Cache
L1 Cache
48 KB (per SM)
48 KB (per SM)
L2 Cache
2.5 MB
2 MB
Performance
Pixel Rate
134.6 GPixel/s
71.30 GPixel/s
Texture Rate
336.6 GTexel/s
178.2 GTexel/s
FP32 (TFLOPS)
10.77 TFLOPS
5.704 TFLOPS
FP64 (TFLOPS)
336.6 GFLOPS (1:32)
178.2 GFLOPS (1:32)
FP16 (TFLOPS)
168.3 GFLOPS (1:64)
89.12 GFLOPS (1:64)
Power
TDP
250 W
75 W
TDP (W)
250
75
-70.0%
Suggested PSU
600 W
250 W
Power Connectors
2x 8-pin
None
Architecture
Architecture
Pascal
Pascal
GPU Name
GP102
GP104
Generation
Mining GPUs
Tesla Pascal
(Pxx)
Process Size
16 nm
16 nm
Transistors
11,800 million
7,200 million
Die Size
471 mm²
314 mm²
Foundry
TSMC
TSMC
Density
25.1M / mm²
22.9M / mm²
API Support
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
6.1
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm
10.5 inches
168 mm
6.6 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Tesla Maxwell
Successor
—
Tesla Volta