GPU Comparison
RADEON
AMD Radeon Vega 8
CORE STATE
Raven
VRAM
System Shared
CLOCK SPEED
1100 MHz
TDP
25 W
BUS WIDTH
System Shared
ARCHITECTURE
GCN 5.0
PROCESS
14 nm
LAUNCH DATE
2018
VS
GEFORCE
Tesla M40
CORE STATE
GM200
VRAM
12 GB
CLOCK SPEED
1112 MHz
TDP
250 W
BUS WIDTH
384 bit
ARCHITECTURE
Maxwell 2.0
PROCESS
28 nm
LAUNCH DATE
2015
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Vega 8
Tesla M40
Core Specs
Shading Units
512
3,072
+500.0%
Shaders
512
3,072
+500.0%
TMUs
32
192
+500.0%
ROPs
8
96
+1100.0%
Compute Units
8
—
Clocks
Base Clock
300 MHz
948 MHz
Boost Clock
1100 MHz
1112 MHz
Memory Clock
System Shared
1502 MHz
6 Gbps effective
Memory
Memory Size
System Shared
12 GB
VRAM (MB)
—
12,288
Memory Type
System Shared
GDDR5
Memory Bus
System Shared
384 bit
Bandwidth
System Dependent
288.4 GB/s
Cache
L1 Cache
—
48 KB (per SMM)
L2 Cache
—
3 MB
Performance
Pixel Rate
8.800 GPixel/s
106.8 GPixel/s
Texture Rate
35.20 GTexel/s
213.5 GTexel/s
FP32 (TFLOPS)
1,126.4 GFLOPS
6.832 TFLOPS
FP64 (TFLOPS)
70.40 GFLOPS (1:16)
213.5 GFLOPS (1:32)
FP16 (TFLOPS)
2.253 TFLOPS (2:1)
—
Power
TDP
25 W
250 W
TDP (W)
25
250
+900.0%
Suggested PSU
—
600 W
Power Connectors
None
8-pin EPS
Architecture
Architecture
GCN 5.0
Maxwell 2.0
GPU Name
Raven
GM200
Generation
Vega IGP
(Raven Ridge)
Tesla Maxwell
(Mxx)
Process Size
14 nm
28 nm
Transistors
4,940 million
8,000 million
Die Size
210 mm²
601 mm²
Foundry
GlobalFoundries
TSMC
Density
23.5M / mm²
13.3M / mm²
API Support
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
5.2
Shader Model
6.7
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Outputs
Motherboard Dependent
No outputs
Bus Interface
IGP
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
GCN 3.0 IGP
Tesla Kepler
Successor
Vega II IGP
Tesla Pascal