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
GEFORCE
A10M
CORE STATE
GA102
VRAM
20 GB
CLOCK SPEED
1635 MHz
TDP
150 W
BUS WIDTH
320 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
—
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_vulkan
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
Pro Vega 16
A10M
Core Specs
Shading Units
1,024
7,168
+600.0%
Shaders
1,024
7,168
+600.0%
TMUs
64
224
+250.0%
ROPs
32
80
+150.0%
Compute Units
16
—
SM Count
—
56
Clocks
Base Clock
815 MHz
975 MHz
Boost Clock
1190 MHz
1635 MHz
Memory Clock
1200 MHz
2.4 Gbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
4 GB
20 GB
VRAM (MB)
4,096
20,480
+400.0%
Memory Type
HBM2
GDDR6
Memory Bus
1024 bit
320 bit
Bandwidth
307.2 GB/s
500.2 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
1024 KB
6 MB
Performance
Pixel Rate
38.08 GPixel/s
130.8 GPixel/s
Texture Rate
76.16 GTexel/s
366.2 GTexel/s
FP32 (TFLOPS)
2.437 TFLOPS
23.44 TFLOPS
FP64 (TFLOPS)
152.3 GFLOPS (1:16)
732.5 GFLOPS (1:32)
FP16 (TFLOPS)
4.874 TFLOPS (2:1)
23.44 TFLOPS (1:1)
AI/RT
RT Cores
—
56
Tensor Cores
—
224
Power
TDP
75 W
150 W
TDP (W)
75
150
+100.0%
Suggested PSU
—
450 W
Power Connectors
—
8-pin EPS
Architecture
Architecture
GCN 5.0
Ampere
GPU Name
Vega 12
GA102
Generation
Radeon Pro Mac
(Vega Series)
Server Ampere
(Axx)
Process Size
14 nm
8 nm
Transistors
—
28,300 million
Die Size
—
628 mm²
Foundry
GlobalFoundries
Samsung
Density
—
45.1M / 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
6.0
6.8
Physical
Slot Width
IGP
Single-slot
Length
—
267 mm
10.5 inches
Height
—
112 mm
4.4 inches
Outputs
Portable Device Dependent
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Tesla Turing
Successor
—
Server Ada