GPU Comparison
RADEON
AMD Radeon Vega 8
CORE STATE
Raven
VRAM
System Shared
CLOCK SPEED
1100 MHz
TDP
25 W
BUS WIDTH
System Shared
ARCHITECTURE
GCN 5.0
PROCESS
14 nm
LAUNCH DATE
2018
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
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Vega 8
A2
Core Specs
Shading Units
512
1,280
+150.0%
Shaders
512
1,280
+150.0%
TMUs
32
40
+25.0%
ROPs
8
32
+300.0%
Compute Units
8
—
SM Count
—
10
Clocks
Base Clock
300 MHz
1440 MHz
Boost Clock
1100 MHz
1770 MHz
Memory Clock
System Shared
1563 MHz
12.5 Gbps effective
Memory
Memory Size
System Shared
16 GB
VRAM (MB)
—
16,384
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
128 bit
Bandwidth
System Dependent
200.1 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
—
2 MB
Performance
Pixel Rate
8.800 GPixel/s
56.64 GPixel/s
Texture Rate
35.20 GTexel/s
70.80 GTexel/s
FP32 (TFLOPS)
1,126.4 GFLOPS
4.531 TFLOPS
FP64 (TFLOPS)
70.40 GFLOPS (1:16)
70.80 GFLOPS (1:64)
FP16 (TFLOPS)
2.253 TFLOPS (2:1)
4.531 TFLOPS (1:1)
AI/RT
RT Cores
—
10
Tensor Cores
—
40
Power
TDP
25 W
60 W
TDP (W)
25
60
+140.0%
Suggested PSU
—
250 W
Power Connectors
None
None
Architecture
Architecture
GCN 5.0
Ampere
GPU Name
Raven
GA107
Generation
Vega IGP
(Raven Ridge)
Workstation Ampere
(Ax000)
Process Size
14 nm
8 nm
Transistors
4,940 million
8,700 million
Die Size
210 mm²
200 mm²
Foundry
GlobalFoundries
Samsung
Density
23.5M / 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
IGP
Single-slot
Outputs
Motherboard Dependent
No outputs
Bus Interface
IGP
PCIe 4.0 x8
Other
Production
End-of-life
End-of-life
Predecessor
GCN 3.0 IGP
Quadro Turing
Successor
Vega II IGP
Workstation Ada