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 T4
CORE STATE
TU104
VRAM
16 GB
CLOCK SPEED
1590 MHz
TDP
70 W
BUS WIDTH
256 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2018
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
A2
Tesla T4
Core Specs
Shading Units
1,280
2,560
+100.0%
Shaders
1,280
2,560
+100.0%
TMUs
40
160
+300.0%
ROPs
32
64
+100.0%
SM Count
10
40
+300.0%
Clocks
Base Clock
1440 MHz
585 MHz
Boost Clock
1770 MHz
1590 MHz
Memory Clock
1563 MHz
12.5 Gbps effective
1250 MHz
10 Gbps effective
Memory
Memory Size
16 GB
16 GB
VRAM (MB)
16,384
16,384
0.0%
Memory Type
GDDR6
GDDR6
Memory Bus
128 bit
256 bit
Bandwidth
200.1 GB/s
320.0 GB/s
Cache
L1 Cache
128 KB (per SM)
64 KB (per SM)
L2 Cache
2 MB
4 MB
Performance
Pixel Rate
56.64 GPixel/s
101.8 GPixel/s
Texture Rate
70.80 GTexel/s
254.4 GTexel/s
FP32 (TFLOPS)
4.531 TFLOPS
8.141 TFLOPS
FP64 (TFLOPS)
70.80 GFLOPS (1:64)
254.4 GFLOPS (1:32)
FP16 (TFLOPS)
4.531 TFLOPS (1:1)
65.13 TFLOPS (8:1)
AI/RT
RT Cores
10
40
+300.0%
Tensor Cores
40
320
+700.0%
Power
TDP
60 W
70 W
TDP (W)
60
70
+16.7%
Suggested PSU
250 W
250 W
Power Connectors
None
None
Architecture
Architecture
Ampere
Turing
GPU Name
GA107
TU104
Generation
Workstation Ampere
(Ax000)
Tesla Turing
(Txx)
Process Size
8 nm
12 nm
Transistors
8,700 million
13,600 million
Die Size
200 mm²
545 mm²
Foundry
Samsung
TSMC
Density
43.5M / mm²
25.0M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.6
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Single-slot
Single-slot
Length
—
168 mm
6.6 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x8
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Quadro Turing
Tesla Volta
Successor
Workstation Ada
Server Ampere