GPU Comparison
GEFORCE
NVIDIA Tesla K20m
CORE STATE
GK110
VRAM
5 GB
CLOCK SPEED
—
TDP
225 W
BUS WIDTH
320 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2013
VS
GEFORCE
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
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Tesla K20m
Tesla P40
Core Specs
Shading Units
2,496
3,840
+53.8%
Shaders
2,496
3,840
+53.8%
TMUs
208
240
+15.4%
ROPs
40
96
+140.0%
SM Count
—
30
Clocks
Base Clock
—
1303 MHz
Boost Clock
—
1531 MHz
GPU Clock
706 MHz
—
Memory Clock
1300 MHz
5.2 Gbps effective
1808 MHz
7.2 Gbps effective
Memory
Memory Size
5 GB
24 GB
VRAM (MB)
5,120
24,576
+380.0%
Memory Type
GDDR5
GDDR5
Memory Bus
320 bit
384 bit
Bandwidth
208.0 GB/s
347.1 GB/s
Cache
L1 Cache
16 KB (per SMX)
48 KB (per SM)
L2 Cache
1280 KB
3 MB
Performance
Pixel Rate
36.71 GPixel/s
147.0 GPixel/s
Texture Rate
146.8 GTexel/s
367.4 GTexel/s
FP32 (TFLOPS)
3.524 TFLOPS
11.76 TFLOPS
FP64 (TFLOPS)
1,174.8 GFLOPS (1:3)
367.4 GFLOPS (1:32)
FP16 (TFLOPS)
—
183.7 GFLOPS (1:64)
Power
TDP
225 W
250 W
TDP (W)
225
250
+11.1%
Suggested PSU
550 W
600 W
Power Connectors
1x 6-pin + 1x 8-pin
8-pin EPS
Architecture
Architecture
Kepler
Pascal
GPU Name
GK110
GP102
Generation
Tesla Kepler
(Kxx)
Tesla Pascal
(Pxx)
Process Size
28 nm
16 nm
Transistors
7,080 million
11,800 million
Die Size
561 mm²
471 mm²
Foundry
TSMC
TSMC
Density
12.6M / mm²
25.1M / mm²
API Support
DirectX
12 (11_0)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.2.175
1.4
OpenCL
3.0
3.0
CUDA
3.5
6.1
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 2.0 x16
PCIe 3.0 x16
Other
Launch Price
3,199 USD
5,699 USD
Production
End-of-life
End-of-life
Predecessor
Tesla Fermi
Tesla Maxwell
Successor
Tesla Maxwell
Tesla Volta