GPU Comparison
GEFORCE
NVIDIA P104-100
CORE STATE
GP104
VRAM
4 GB
CLOCK SPEED
1733 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
VS
GEFORCE
Tesla K20Xm
CORE STATE
GK110
VRAM
6 GB
CLOCK SPEED
—
TDP
235 W
BUS WIDTH
384 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2012
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
geekbench_metal
DETAILED SPECIFICATIONS
SPECIFICATION
P104-100
Tesla K20Xm
Core Specs
Shading Units
1,920
2,688
+40.0%
Shaders
1,920
2,688
+40.0%
TMUs
120
224
+86.7%
ROPs
64
48
-25.0%
SM Count
15
—
Clocks
Base Clock
1607 MHz
—
Boost Clock
1733 MHz
—
GPU Clock
—
732 MHz
Memory Clock
1251 MHz
10 Gbps effective
1300 MHz
5.2 Gbps effective
Memory
Memory Size
4 GB
6 GB
VRAM (MB)
4,096
6,144
+50.0%
Memory Type
GDDR5X
GDDR5
Memory Bus
256 bit
384 bit
Bandwidth
320.3 GB/s
249.6 GB/s
Cache
L1 Cache
48 KB (per SM)
16 KB (per SMX)
L2 Cache
2 MB
1536 KB
Performance
Pixel Rate
110.9 GPixel/s
40.99 GPixel/s
Texture Rate
208.0 GTexel/s
164.0 GTexel/s
FP32 (TFLOPS)
6.655 TFLOPS
3.935 TFLOPS
FP64 (TFLOPS)
208.0 GFLOPS (1:32)
1,311.7 GFLOPS (1:3)
FP16 (TFLOPS)
104.0 GFLOPS (1:64)
—
Power
TDP
—
235 W
TDP (W)
—
235
Suggested PSU
200 W
550 W
Power Connectors
1x 8-pin
—
Architecture
Architecture
Pascal
Kepler
GPU Name
GP104
GK110
Generation
Mining GPUs
Tesla Kepler
(Kxx)
Process Size
16 nm
28 nm
Transistors
7,200 million
7,080 million
Die Size
314 mm²
561 mm²
Foundry
TSMC
TSMC
Density
22.9M / mm²
12.6M / mm²
API Support
DirectX
12 (12_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.2.175
OpenCL
3.0
3.0
CUDA
6.1
3.5
Shader Model
6.8
6.5 (5.1)
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 3.0 x16
Other
Launch Price
—
7,699 USD
Production
End-of-life
End-of-life
Predecessor
—
Tesla Fermi
Successor
—
Tesla Maxwell