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
GeForce GTX 1050 Ti
CORE STATE
GP107
VRAM
4 GB
CLOCK SPEED
1392 MHz
TDP
75 W
BUS WIDTH
128 bit
ARCHITECTURE
Pascal
PROCESS
14 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
geekbench_metal
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
A2
GTX 1050 Ti
Core Specs
Shading Units
1,280
768
-40.0%
Shaders
1,280
768
-40.0%
TMUs
40
48
+20.0%
ROPs
32
32
0.0%
SM Count
10
6
-40.0%
Clocks
Base Clock
1440 MHz
1291 MHz
Boost Clock
1770 MHz
1392 MHz
Memory Clock
1563 MHz
12.5 Gbps effective
1752 MHz
7 Gbps effective
Memory
Memory Size
16 GB
4 GB
VRAM (MB)
16,384
4,096
-75.0%
Memory Type
GDDR6
GDDR5
Memory Bus
128 bit
128 bit
Bandwidth
200.1 GB/s
112.1 GB/s
Cache
L1 Cache
128 KB (per SM)
48 KB (per SM)
L2 Cache
2 MB
1024 KB
Performance
Pixel Rate
56.64 GPixel/s
44.54 GPixel/s
Texture Rate
70.80 GTexel/s
66.82 GTexel/s
FP32 (TFLOPS)
4.531 TFLOPS
2.138 TFLOPS
FP64 (TFLOPS)
70.80 GFLOPS (1:64)
66.82 GFLOPS (1:32)
FP16 (TFLOPS)
4.531 TFLOPS (1:1)
33.41 GFLOPS (1:64)
AI/RT
RT Cores
10
—
Tensor Cores
40
—
Power
TDP
60 W
75 W
TDP (W)
60
75
+25.0%
Suggested PSU
250 W
250 W
Power Connectors
None
None
Architecture
Architecture
Ampere
Pascal
GPU Name
GA107
GP107
Generation
Workstation Ampere
(Ax000)
GeForce 10
Process Size
8 nm
14 nm
Transistors
8,700 million
3,300 million
Die Size
200 mm²
132 mm²
Foundry
Samsung
Samsung
Density
43.5M / mm²
25.0M / 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
—
145 mm
5.7 inches
Height
—
111 mm
4.4 inches
Outputs
No outputs
1x DVI1x HDMI 2.01x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x8
PCIe 3.0 x16
Other
Launch Price
—
139 USD
Production
End-of-life
End-of-life
Predecessor
Quadro Turing
GeForce 900
Successor
Workstation Ada
GeForce 20