GPU Comparison
RADEON
AMD Radeon Pro Vega 20
CORE STATE
Vega 12
VRAM
4 GB
CLOCK SPEED
1283 MHz
TDP
100 W
BUS WIDTH
1024 bit
ARCHITECTURE
GCN 5.0
PROCESS
14 nm
LAUNCH DATE
2018
VS
GEFORCE
Tesla M10
CORE STATE
GM107
VRAM
8 GB
CLOCK SPEED
1306 MHz
TDP
225 W
BUS WIDTH
128 bit
ARCHITECTURE
Maxwell
PROCESS
28 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Pro Vega 20
Tesla M10
Core Specs
Shading Units
1,280
640
-50.0%
Shaders
1,280
640
-50.0%
TMUs
80
40
-50.0%
ROPs
32
16
-50.0%
Compute Units
20
—
Clocks
Base Clock
815 MHz
1033 MHz
Boost Clock
1283 MHz
1306 MHz
Memory Clock
740 MHz
1480 Mbps effective
1300 MHz
5.2 Gbps effective
Memory
Memory Size
4 GB
8 GB
VRAM (MB)
4,096
8,192
+100.0%
Memory Type
HBM2
GDDR5
Memory Bus
1024 bit
128 bit
Bandwidth
189.4 GB/s
83.20 GB/s
Cache
L1 Cache
16 KB (per CU)
64 KB (per SMM)
L2 Cache
1024 KB
2 MB
Performance
Pixel Rate
41.06 GPixel/s
20.90 GPixel/s
Texture Rate
102.6 GTexel/s
52.24 GTexel/s
FP32 (TFLOPS)
3.284 TFLOPS
1.672 TFLOPS
FP64 (TFLOPS)
205.3 GFLOPS (1:16)
52.24 GFLOPS (1:32)
FP16 (TFLOPS)
6.569 TFLOPS (2:1)
—
Power
TDP
100 W
225 W
TDP (W)
100
225
+125.0%
Suggested PSU
—
550 W
Power Connectors
—
1x 8-pin
Architecture
Architecture
GCN 5.0
Maxwell
GPU Name
Vega 12
GM107
Generation
Radeon Pro Mac
(Vega Series)
Tesla Maxwell
(Mxx)
Process Size
14 nm
28 nm
Transistors
—
1,870 million
Die Size
—
148 mm²
Foundry
GlobalFoundries
TSMC
Density
—
12.6M / mm²
API Support
DirectX
12 (12_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
5.0
Shader Model
6.0
6.7 (5.1)
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Outputs
Portable Device Dependent
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Tesla Kepler
Successor
—
Tesla Pascal