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
GPU
Arc A770M
CORE STATE
DG2-512
VRAM
16 GB
CLOCK SPEED
2050 MHz
TDP
120 W
BUS WIDTH
256 bit
ARCHITECTURE
Xe-HPG
PROCESS
6 nm
LAUNCH DATE
—
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
3dmark_3dmark_steel_nomad_dx12
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
Vega 8
A770M
Core Specs
Shading Units
512
4,096
+700.0%
Shaders
512
4,096
+700.0%
TMUs
32
256
+700.0%
ROPs
8
128
+1500.0%
Compute Units
8
—
Execution Units
—
512
Clocks
Base Clock
300 MHz
1650 MHz
Boost Clock
1100 MHz
2050 MHz
Memory Clock
System Shared
2000 MHz
16 Gbps effective
Memory
Memory Size
System Shared
16 GB
VRAM (MB)
—
16,384
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
256 bit
Bandwidth
System Dependent
512.0 GB/s
Cache
L2 Cache
—
16 MB
Performance
Pixel Rate
8.800 GPixel/s
262.4 GPixel/s
Texture Rate
35.20 GTexel/s
524.8 GTexel/s
FP32 (TFLOPS)
1,126.4 GFLOPS
16.79 TFLOPS
FP64 (TFLOPS)
70.40 GFLOPS (1:16)
—
FP16 (TFLOPS)
2.253 TFLOPS (2:1)
33.59 TFLOPS (2:1)
AI/RT
RT Cores
—
32
XMX Cores
—
512
Power
TDP
25 W
120 W
TDP (W)
25
120
+380.0%
Power Connectors
None
—
Architecture
Architecture
GCN 5.0
Xe-HPG
GPU Name
Raven
DG2-512
Generation
Vega IGP
(Raven Ridge)
Alchemist
(Arc 7 Mobile)
Process Size
14 nm
6 nm
Transistors
4,940 million
21,700 million
Die Size
210 mm²
406 mm²
Foundry
GlobalFoundries
TSMC
Density
23.5M / mm²
53.4M / 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
Shader Model
6.7
6.6
Physical
Slot Width
IGP
IGP
Outputs
Motherboard Dependent
Portable Device Dependent
Bus Interface
IGP
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
GCN 3.0 IGP
—
Successor
Vega II IGP
—