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 M40
CORE STATE
GM200
VRAM
12 GB
CLOCK SPEED
1112 MHz
TDP
250 W
BUS WIDTH
384 bit
ARCHITECTURE
Maxwell 2.0
PROCESS
28 nm
LAUNCH DATE
2015
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
P104-100
Tesla M40
Core Specs
Shading Units
1,920
3,072
+60.0%
Shaders
1,920
3,072
+60.0%
TMUs
120
192
+60.0%
ROPs
64
96
+50.0%
SM Count
15
—
Clocks
Base Clock
1607 MHz
948 MHz
Boost Clock
1733 MHz
1112 MHz
Memory Clock
1251 MHz
10 Gbps effective
1502 MHz
6 Gbps effective
Memory
Memory Size
4 GB
12 GB
VRAM (MB)
4,096
12,288
+200.0%
Memory Type
GDDR5X
GDDR5
Memory Bus
256 bit
384 bit
Bandwidth
320.3 GB/s
288.4 GB/s
Cache
L1 Cache
48 KB (per SM)
48 KB (per SMM)
L2 Cache
2 MB
3 MB
Performance
Pixel Rate
110.9 GPixel/s
106.8 GPixel/s
Texture Rate
208.0 GTexel/s
213.5 GTexel/s
FP32 (TFLOPS)
6.655 TFLOPS
6.832 TFLOPS
FP64 (TFLOPS)
208.0 GFLOPS (1:32)
213.5 GFLOPS (1:32)
FP16 (TFLOPS)
104.0 GFLOPS (1:64)
—
Power
TDP
—
250 W
TDP (W)
—
250
Suggested PSU
200 W
600 W
Power Connectors
1x 8-pin
8-pin EPS
Architecture
Architecture
Pascal
Maxwell 2.0
GPU Name
GP104
GM200
Generation
Mining GPUs
Tesla Maxwell
(Mxx)
Process Size
16 nm
28 nm
Transistors
7,200 million
8,000 million
Die Size
314 mm²
601 mm²
Foundry
TSMC
TSMC
Density
22.9M / mm²
13.3M / 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
5.2
Shader Model
6.8
6.8
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
Production
End-of-life
End-of-life
Predecessor
—
Tesla Kepler
Successor
—
Tesla Pascal