GPU Comparison
GEFORCE
NVIDIA A2
CORE STATE
GA107
VRAM
16 GB
CLOCK SPEED
1770 MHz
TDP
60 W
BUS WIDTH
128 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
VS
GEFORCE
Tesla P40
CORE STATE
GP102
VRAM
24 GB
CLOCK SPEED
1531 MHz
TDP
250 W
BUS WIDTH
384 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
A2
Tesla P40
Core Specs
Shading Units
1,280
3,840
+200.0%
Shaders
1,280
3,840
+200.0%
TMUs
40
240
+500.0%
ROPs
32
96
+200.0%
SM Count
10
30
+200.0%
Clocks
Base Clock
1440 MHz
1303 MHz
Boost Clock
1770 MHz
1531 MHz
Memory Clock
1563 MHz
12.5 Gbps effective
1808 MHz
7.2 Gbps effective
Memory
Memory Size
16 GB
24 GB
VRAM (MB)
16,384
24,576
+50.0%
Memory Type
GDDR6
GDDR5
Memory Bus
128 bit
384 bit
Bandwidth
200.1 GB/s
347.1 GB/s
Cache
L1 Cache
128 KB (per SM)
48 KB (per SM)
L2 Cache
2 MB
3 MB
Performance
Pixel Rate
56.64 GPixel/s
147.0 GPixel/s
Texture Rate
70.80 GTexel/s
367.4 GTexel/s
FP32 (TFLOPS)
4.531 TFLOPS
11.76 TFLOPS
FP64 (TFLOPS)
70.80 GFLOPS (1:64)
367.4 GFLOPS (1:32)
FP16 (TFLOPS)
4.531 TFLOPS (1:1)
183.7 GFLOPS (1:64)
AI/RT
RT Cores
10
—
Tensor Cores
40
—
Power
TDP
60 W
250 W
TDP (W)
60
250
+316.7%
Suggested PSU
250 W
600 W
Power Connectors
None
8-pin EPS
Architecture
Architecture
Ampere
Pascal
GPU Name
GA107
GP102
Generation
Workstation Ampere
(Ax000)
Tesla Pascal
(Pxx)
Process Size
8 nm
16 nm
Transistors
8,700 million
11,800 million
Die Size
200 mm²
471 mm²
Foundry
Samsung
TSMC
Density
43.5M / mm²
25.1M / 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
8.6
6.1
Shader Model
6.8
6.8
Physical
Slot Width
Single-slot
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x8
PCIe 3.0 x16
Other
Launch Price
—
5,699 USD
Production
End-of-life
End-of-life
Predecessor
Quadro Turing
Tesla Maxwell
Successor
Workstation Ada
Tesla Volta