GPU Comparison
RADEON
AMD Radeon Pro Vega 64
CORE STATE
Vega 10
VRAM
16 GB
CLOCK SPEED
1350 MHz
TDP
250 W
BUS WIDTH
2048 bit
ARCHITECTURE
GCN 5.0
PROCESS
14 nm
LAUNCH DATE
2017
VS
GPU
Iris Pro Graphics 5200
CORE STATE
Haswell GT3e
VRAM
System Shared
CLOCK SPEED
1150 MHz
TDP
45 W
BUS WIDTH
System Shared
ARCHITECTURE
Generation 7.5
PROCESS
22 nm
LAUNCH DATE
2013
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Pro Vega 64
Iris Pro Graphics 5200
Core Specs
Shading Units
4,096
320
-92.2%
Shaders
4,096
320
-92.2%
TMUs
256
40
-84.4%
ROPs
64
4
-93.8%
Compute Units
64
—
Execution Units
—
40
Clocks
Base Clock
1250 MHz
200 MHz
Boost Clock
1350 MHz
1150 MHz
Memory Clock
786 MHz
1572 Mbps effective
System Shared
Memory
Memory Size
16 GB
System Shared
VRAM (MB)
16,384
—
Memory Type
HBM2
System Shared
Memory Bus
2048 bit
System Shared
Bandwidth
402.4 GB/s
System Dependent
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
4 MB
—
Performance
Pixel Rate
86.40 GPixel/s
4.600 GPixel/s
Texture Rate
345.6 GTexel/s
46.00 GTexel/s
FP32 (TFLOPS)
11.06 TFLOPS
736.0 GFLOPS
FP64 (TFLOPS)
691.2 GFLOPS (1:16)
184.0 GFLOPS (1:4)
FP16 (TFLOPS)
22.12 TFLOPS (2:1)
—
Power
TDP
250 W
45 W
TDP (W)
250
45
-82.0%
Power Connectors
None
—
Architecture
Architecture
GCN 5.0
Generation 7.5
GPU Name
Vega 10
Haswell GT3e
Generation
Radeon Pro Mac
(Vega Series)
HD Graphics
(Haswell)
Process Size
14 nm
22 nm
Transistors
12,500 million
—
Die Size
495 mm²
—
Foundry
GlobalFoundries
Intel
Density
25.3M / mm²
—
API Support
DirectX
12 (12_1)
12 (11_1)
OpenGL
4.6
4.3
Vulkan
1.3
1.0
OpenCL
2.1
1.2
Shader Model
6.7
5.1
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