GPU Comparison
RADEON
AMD Radeon Pro Vega 16
CORE STATE
Vega 12
VRAM
4 GB
CLOCK SPEED
1190 MHz
TDP
75 W
BUS WIDTH
1024 bit
ARCHITECTURE
GCN 5.0
PROCESS
14 nm
LAUNCH DATE
2018
VS
GPU
Iris Pro Graphics P580
CORE STATE
Skylake GT4e
VRAM
System Shared
CLOCK SPEED
1000 MHz
TDP
15 W
BUS WIDTH
System Shared
ARCHITECTURE
Generation 9.0
PROCESS
14 nm+
LAUNCH DATE
2015
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_vulkan
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
Pro Vega 16
Iris Pro Graphics P580
Core Specs
Shading Units
1,024
576
-43.8%
Shaders
1,024
576
-43.8%
TMUs
64
72
+12.5%
ROPs
32
9
-71.9%
Compute Units
16
—
Execution Units
—
72
Clocks
Base Clock
815 MHz
350 MHz
Boost Clock
1190 MHz
1000 MHz
Memory Clock
1200 MHz
2.4 Gbps effective
System Shared
Memory
Memory Size
4 GB
System Shared
VRAM (MB)
4,096
—
Memory Type
HBM2
System Shared
Memory Bus
1024 bit
System Shared
Bandwidth
307.2 GB/s
System Dependent
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
1024 KB
—
Performance
Pixel Rate
38.08 GPixel/s
9.000 GPixel/s
Texture Rate
76.16 GTexel/s
72.00 GTexel/s
FP32 (TFLOPS)
2.437 TFLOPS
1,152.0 GFLOPS
FP64 (TFLOPS)
152.3 GFLOPS (1:16)
288.0 GFLOPS (1:4)
FP16 (TFLOPS)
4.874 TFLOPS (2:1)
2.304 TFLOPS (2:1)
Power
TDP
75 W
15 W
TDP (W)
75
15
-80.0%
Architecture
Architecture
GCN 5.0
Generation 9.0
GPU Name
Vega 12
Skylake GT4e
Generation
Radeon Pro Mac
(Vega Series)
HD Graphics-W
(Skylake)
Process Size
14 nm
14 nm+
Foundry
GlobalFoundries
Intel
API Support
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.3
1.3
OpenCL
2.1
3.0
Shader Model
6.0
6.4
Physical
Slot Width
IGP
IGP
Outputs
Portable Device Dependent
Motherboard Dependent
Bus Interface
PCIe 3.0 x16
Ring Bus
Other
Production
End-of-life
End-of-life