GPU Comparison
GEFORCE
NVIDIA Tesla P40
CORE STATE
GP102
VRAM
24 GB
CLOCK SPEED
1531 MHz
TDP
250 W
BUS WIDTH
384 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2016
VS
GEFORCE
Tesla T4
CORE STATE
TU104
VRAM
16 GB
CLOCK SPEED
1590 MHz
TDP
70 W
BUS WIDTH
256 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2018
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Tesla P40
Tesla T4
Core Specs
Shading Units
3,840
2,560
-33.3%
Shaders
3,840
2,560
-33.3%
TMUs
240
160
-33.3%
ROPs
96
64
-33.3%
SM Count
30
40
+33.3%
Clocks
Base Clock
1303 MHz
585 MHz
Boost Clock
1531 MHz
1590 MHz
Memory Clock
1808 MHz
7.2 Gbps effective
1250 MHz
10 Gbps effective
Memory
Memory Size
24 GB
16 GB
VRAM (MB)
24,576
16,384
-33.3%
Memory Type
GDDR5
GDDR6
Memory Bus
384 bit
256 bit
Bandwidth
347.1 GB/s
320.0 GB/s
Cache
L1 Cache
48 KB (per SM)
64 KB (per SM)
L2 Cache
3 MB
4 MB
Performance
Pixel Rate
147.0 GPixel/s
101.8 GPixel/s
Texture Rate
367.4 GTexel/s
254.4 GTexel/s
FP32 (TFLOPS)
11.76 TFLOPS
8.141 TFLOPS
FP64 (TFLOPS)
367.4 GFLOPS (1:32)
254.4 GFLOPS (1:32)
FP16 (TFLOPS)
183.7 GFLOPS (1:64)
65.13 TFLOPS (8:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
320
Power
TDP
250 W
70 W
TDP (W)
250
70
-72.0%
Suggested PSU
600 W
250 W
Power Connectors
8-pin EPS
None
Architecture
Architecture
Pascal
Turing
GPU Name
GP102
TU104
Generation
Tesla Pascal
(Pxx)
Tesla Turing
(Txx)
Process Size
16 nm
12 nm
Transistors
11,800 million
13,600 million
Die Size
471 mm²
545 mm²
Foundry
TSMC
TSMC
Density
25.1M / mm²
25.0M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm
10.5 inches
168 mm
6.6 inches
Height
111 mm
4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
5,699 USD
—
Production
End-of-life
End-of-life
Predecessor
Tesla Maxwell
Tesla Volta
Successor
Tesla Volta
Server Ampere