GPU Comparison
GEFORCE
NVIDIA CMP 40HX
CORE STATE
TU106
VRAM
8 GB
CLOCK SPEED
1650 MHz
TDP
185 W
BUS WIDTH
256 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2021
VS
GEFORCE
Tesla M4
CORE STATE
GM206
VRAM
4 GB
CLOCK SPEED
1072 MHz
TDP
50 W
BUS WIDTH
128 bit
ARCHITECTURE
Maxwell 2.0
PROCESS
28 nm
LAUNCH DATE
2015
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 40HX
Tesla M4
Core Specs
Shading Units
2,304
1,024
-55.6%
Shaders
2,304
1,024
-55.6%
TMUs
144
64
-55.6%
ROPs
64
32
-50.0%
SM Count
36
—
Clocks
Base Clock
1470 MHz
872 MHz
Boost Clock
1650 MHz
1072 MHz
Memory Clock
1750 MHz
14 Gbps effective
1375 MHz
5.5 Gbps effective
Memory
Memory Size
8 GB
4 GB
VRAM (MB)
8,192
4,096
-50.0%
Memory Type
GDDR6
GDDR5
Memory Bus
256 bit
128 bit
Bandwidth
448.0 GB/s
88.00 GB/s
Cache
L1 Cache
64 KB (per SM)
48 KB (per SMM)
L2 Cache
4 MB
1024 KB
Performance
Pixel Rate
105.6 GPixel/s
34.30 GPixel/s
Texture Rate
237.6 GTexel/s
68.61 GTexel/s
FP32 (TFLOPS)
7.603 TFLOPS
2.195 TFLOPS
FP64 (TFLOPS)
237.6 GFLOPS (1:32)
68.61 GFLOPS (1:32)
FP16 (TFLOPS)
15.21 TFLOPS (2:1)
—
AI/RT
RT Cores
36
—
Tensor Cores
288
—
Power
TDP
185 W
50 W
TDP (W)
185
50
-73.0%
Suggested PSU
450 W
250 W
Power Connectors
1x 8-pin
—
Architecture
Architecture
Turing
Maxwell 2.0
GPU Name
TU106
GM206
Generation
Mining GPUs
Tesla Maxwell
(Mxx)
Process Size
12 nm
28 nm
Transistors
10,800 million
2,940 million
Die Size
445 mm²
228 mm²
Foundry
TSMC
TSMC
Density
24.3M / mm²
12.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
7.5
5.2
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
229 mm
9 inches
—
Height
111 mm
4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 3.0 x16
Other
Launch Price
699 USD
—
Production
End-of-life
End-of-life
Predecessor
—
Tesla Kepler
Successor
—
Tesla Pascal