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
L40
CORE STATE
AD102
VRAM
48 GB
CLOCK SPEED
2490 MHz
TDP
300 W
BUS WIDTH
384 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Pro Vega 20
L40
Core Specs
Shading Units
1,280
18,176
+1320.0%
Shaders
1,280
18,176
+1320.0%
TMUs
80
568
+610.0%
ROPs
32
192
+500.0%
Compute Units
20
—
SM Count
—
142
Clocks
Base Clock
815 MHz
735 MHz
Boost Clock
1283 MHz
2490 MHz
Memory Clock
740 MHz
1480 Mbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
4 GB
48 GB
VRAM (MB)
4,096
49,152
+1100.0%
Memory Type
HBM2
GDDR6
Memory Bus
1024 bit
384 bit
Bandwidth
189.4 GB/s
864.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
1024 KB
96 MB
Performance
Pixel Rate
41.06 GPixel/s
478.1 GPixel/s
Texture Rate
102.6 GTexel/s
1,414.3 GTexel/s
FP32 (TFLOPS)
3.284 TFLOPS
90.52 TFLOPS
FP64 (TFLOPS)
205.3 GFLOPS (1:16)
1,414.3 GFLOPS (1:64)
FP16 (TFLOPS)
6.569 TFLOPS (2:1)
90.52 TFLOPS (1:1)
AI/RT
RT Cores
—
142
Tensor Cores
—
568
Power
TDP
100 W
300 W
TDP (W)
100
300
+200.0%
Suggested PSU
—
700 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
GCN 5.0
Ada Lovelace
GPU Name
Vega 12
AD102
Generation
Radeon Pro Mac
(Vega Series)
Server Ada
(Lxx)
Process Size
14 nm
5 nm
Transistors
—
76,300 million
Die Size
—
609 mm²
Foundry
GlobalFoundries
TSMC
Density
—
125.3M / 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
—
8.9
Shader Model
6.0
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
Portable Device Dependent
4x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Server Ampere
Successor
—
Server Hopper