GPU Comparison
GEFORCE
NVIDIA P106-090
CORE STATE
GP106
VRAM
3 GB
CLOCK SPEED
1531 MHz
TDP
75 W
BUS WIDTH
192 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
VS
GEFORCE
Tesla M10
CORE STATE
GM107
VRAM
8 GB
CLOCK SPEED
1306 MHz
TDP
225 W
BUS WIDTH
128 bit
ARCHITECTURE
Maxwell
PROCESS
28 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
P106-090
Tesla M10
Core Specs
Shading Units
768
640
-16.7%
Shaders
768
640
-16.7%
TMUs
48
40
-16.7%
ROPs
48
16
-66.7%
SM Count
6
—
Clocks
Base Clock
1354 MHz
1033 MHz
Boost Clock
1531 MHz
1306 MHz
Memory Clock
2002 MHz
8 Gbps effective
1300 MHz
5.2 Gbps effective
Memory
Memory Size
3 GB
8 GB
VRAM (MB)
3,072
8,192
+166.7%
Memory Type
GDDR5
GDDR5
Memory Bus
192 bit
128 bit
Bandwidth
192.2 GB/s
83.20 GB/s
Cache
L1 Cache
48 KB (per SM)
64 KB (per SMM)
L2 Cache
1536 KB
2 MB
Performance
Pixel Rate
73.49 GPixel/s
20.90 GPixel/s
Texture Rate
73.49 GTexel/s
52.24 GTexel/s
FP32 (TFLOPS)
2.352 TFLOPS
1.672 TFLOPS
FP64 (TFLOPS)
73.49 GFLOPS (1:32)
52.24 GFLOPS (1:32)
FP16 (TFLOPS)
36.74 GFLOPS (1:64)
—
Power
TDP
75 W
225 W
TDP (W)
75
225
+200.0%
Suggested PSU
250 W
550 W
Power Connectors
1x 6-pin
1x 8-pin
Architecture
Architecture
Pascal
Maxwell
GPU Name
GP106
GM107
Generation
Mining GPUs
Tesla Maxwell
(Mxx)
Process Size
16 nm
28 nm
Transistors
4,400 million
1,870 million
Die Size
200 mm²
148 mm²
Foundry
TSMC
TSMC
Density
22.0M / mm²
12.6M / mm²
API Support
DirectX
12 (12_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
5.0
Shader Model
6.8
6.7 (5.1)
Physical
Slot Width
Dual-slot
Dual-slot
Length
250 mm
9.8 inches
267 mm
10.5 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x1
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Tesla Kepler
Successor
—
Tesla Pascal