GPU Comparison
RADEON
AMD Radeon VII
CORE STATE
Vega 20
VRAM
16 GB
CLOCK SPEED
1750 MHz
TDP
295 W
BUS WIDTH
4096 bit
ARCHITECTURE
GCN 5.1
PROCESS
7 nm
LAUNCH DATE
2019
VS
GEFORCE
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
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
VII
A2
Core Specs
Shading Units
3,840
1,280
-66.7%
Shaders
3,840
1,280
-66.7%
TMUs
240
40
-83.3%
ROPs
64
32
-50.0%
Compute Units
60
—
SM Count
—
10
Clocks
Base Clock
1400 MHz
1440 MHz
Boost Clock
1750 MHz
1770 MHz
Memory Clock
1000 MHz
2 Gbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
16 GB
16 GB
VRAM (MB)
16,384
16,384
0.0%
Memory Type
HBM2
GDDR6
Memory Bus
4096 bit
128 bit
Bandwidth
1.02 TB/s
200.1 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
4 MB
2 MB
Performance
Pixel Rate
112.0 GPixel/s
56.64 GPixel/s
Texture Rate
420.0 GTexel/s
70.80 GTexel/s
FP32 (TFLOPS)
13.44 TFLOPS
4.531 TFLOPS
FP64 (TFLOPS)
3.360 TFLOPS (1:4)
70.80 GFLOPS (1:64)
FP16 (TFLOPS)
26.88 TFLOPS (2:1)
4.531 TFLOPS (1:1)
AI/RT
RT Cores
—
10
Tensor Cores
—
40
Power
TDP
295 W
60 W
TDP (W)
295
60
-79.7%
Suggested PSU
600 W
250 W
Power Connectors
2x 8-pin
None
Architecture
Architecture
GCN 5.1
Ampere
GPU Name
Vega 20
GA107
Generation
Vega II
(Radeon VII)
Workstation Ampere
(Ax000)
Process Size
7 nm
8 nm
Transistors
13,230 million
8,700 million
Die Size
331 mm²
200 mm²
Foundry
TSMC
Samsung
Density
40.0M / mm²
43.5M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
8.6
Shader Model
6.7
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
280 mm
11 inches
—
Height
125 mm
4.9 inches
—
Outputs
1x HDMI 2.0b3x DisplayPort 1.4a
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x8
Other
Launch Price
699 USD
—
Production
End-of-life
End-of-life
Predecessor
Vega
Quadro Turing
Successor
Navi
Workstation Ada