GPU Comparison
GEFORCE
NVIDIA A10M
CORE STATE
GA102
VRAM
20 GB
CLOCK SPEED
1635 MHz
TDP
150 W
BUS WIDTH
320 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
—
VS
GEFORCE
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
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
A10M
Tesla K20m
Core Specs
Shading Units
7,168
2,496
-65.2%
Shaders
7,168
2,496
-65.2%
TMUs
224
208
-7.1%
ROPs
80
40
-50.0%
SM Count
56
—
Clocks
Base Clock
975 MHz
—
Boost Clock
1635 MHz
—
GPU Clock
—
706 MHz
Memory Clock
1563 MHz
12.5 Gbps effective
1300 MHz
5.2 Gbps effective
Memory
Memory Size
20 GB
5 GB
VRAM (MB)
20,480
5,120
-75.0%
Memory Type
GDDR6
GDDR5
Memory Bus
320 bit
320 bit
Bandwidth
500.2 GB/s
208.0 GB/s
Cache
L1 Cache
128 KB (per SM)
16 KB (per SMX)
L2 Cache
6 MB
1280 KB
Performance
Pixel Rate
130.8 GPixel/s
36.71 GPixel/s
Texture Rate
366.2 GTexel/s
146.8 GTexel/s
FP32 (TFLOPS)
23.44 TFLOPS
3.524 TFLOPS
FP64 (TFLOPS)
732.5 GFLOPS (1:32)
1,174.8 GFLOPS (1:3)
FP16 (TFLOPS)
23.44 TFLOPS (1:1)
—
AI/RT
RT Cores
56
—
Tensor Cores
224
—
Power
TDP
150 W
225 W
TDP (W)
150
225
+50.0%
Suggested PSU
450 W
550 W
Power Connectors
8-pin EPS
1x 6-pin + 1x 8-pin
Architecture
Architecture
Ampere
Kepler
GPU Name
GA102
GK110
Generation
Server Ampere
(Axx)
Tesla Kepler
(Kxx)
Process Size
8 nm
28 nm
Transistors
28,300 million
7,080 million
Die Size
628 mm²
561 mm²
Foundry
Samsung
TSMC
Density
45.1M / mm²
12.6M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.2.175
OpenCL
3.0
3.0
CUDA
8.6
3.5
Shader Model
6.8
6.5 (5.1)
Physical
Slot Width
Single-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
112 mm
4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16
Other
Launch Price
—
3,199 USD
Production
End-of-life
End-of-life
Predecessor
Tesla Turing
Tesla Fermi
Successor
Server Ada
Tesla Maxwell