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
RADEON
Radeon R7 Graphics
CORE STATE
Spectre Lite
VRAM
System Shared
CLOCK SPEED
—
TDP
25 W
BUS WIDTH
System Shared
ARCHITECTURE
GCN 2.0
PROCESS
28 nm
LAUNCH DATE
2014
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Pro Vega 64
R7 Graphics
Core Specs
Shading Units
4,096
384
-90.6%
Shaders
4,096
384
-90.6%
TMUs
256
24
-90.6%
ROPs
64
8
-87.5%
Compute Units
64
6
-90.6%
Clocks
Base Clock
1250 MHz
—
Boost Clock
1350 MHz
—
GPU Clock
—
720 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
5.760 GPixel/s
Texture Rate
345.6 GTexel/s
17.28 GTexel/s
FP32 (TFLOPS)
11.06 TFLOPS
553.0 GFLOPS
FP64 (TFLOPS)
691.2 GFLOPS (1:16)
34.56 GFLOPS (1:16)
FP16 (TFLOPS)
22.12 TFLOPS (2:1)
—
Power
TDP
250 W
25 W
TDP (W)
250
25
-90.0%
Power Connectors
None
—
Architecture
Architecture
GCN 5.0
GCN 2.0
GPU Name
Vega 10
Spectre Lite
Generation
Radeon Pro Mac
(Vega Series)
GCN 2.0 IGP
(Kaveri)
Process Size
14 nm
28 nm
Transistors
12,500 million
2,410 million
Die Size
495 mm²
245 mm²
Foundry
GlobalFoundries
GlobalFoundries
Density
25.3M / mm²
9.8M / mm²
API Support
DirectX
12 (12_1)
12 (12_0)
OpenGL
4.6
4.6
Vulkan
1.3
1.2.170
OpenCL
2.1
2.1
Shader Model
6.7
6.5
Physical
Slot Width
IGP
IGP
Outputs
Portable Device Dependent
Motherboard Dependent
Bus Interface
PCIe 3.0 x16
IGP
Other
Production
End-of-life
End-of-life
Predecessor
—
TeraScale 3 IGP
Successor
—
GCN 3.0 IGP