GPU Comparison
RADEON
AMD Radeon Vega 3
CORE STATE
Picasso
VRAM
System Shared
CLOCK SPEED
1100 MHz
TDP
15 W
BUS WIDTH
System Shared
ARCHITECTURE
GCN 5.0
PROCESS
12 nm
LAUNCH DATE
2019
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
Vega 3
L40
Core Specs
Shading Units
192
18,176
+9366.7%
Shaders
192
18,176
+9366.7%
TMUs
12
568
+4633.3%
ROPs
4
192
+4700.0%
Compute Units
3
—
SM Count
—
142
Clocks
Base Clock
300 MHz
735 MHz
Boost Clock
1100 MHz
2490 MHz
Memory Clock
System Shared
2250 MHz
18 Gbps effective
Memory
Memory Size
System Shared
48 GB
VRAM (MB)
—
49,152
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
384 bit
Bandwidth
System Dependent
864.0 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
—
96 MB
Performance
Pixel Rate
4.400 GPixel/s
478.1 GPixel/s
Texture Rate
13.20 GTexel/s
1,414.3 GTexel/s
FP32 (TFLOPS)
422.4 GFLOPS
90.52 TFLOPS
FP64 (TFLOPS)
26.40 GFLOPS (1:16)
1,414.3 GFLOPS (1:64)
FP16 (TFLOPS)
844.8 GFLOPS (2:1)
90.52 TFLOPS (1:1)
AI/RT
RT Cores
—
142
Tensor Cores
—
568
Power
TDP
15 W
300 W
TDP (W)
15
300
+1900.0%
Suggested PSU
—
700 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
GCN 5.0
Ada Lovelace
GPU Name
Picasso
AD102
Generation
Vega IGP
(Picasso)
Server Ada
(Lxx)
Process Size
12 nm
5 nm
Transistors
4,940 million
76,300 million
Die Size
210 mm²
609 mm²
Foundry
GlobalFoundries
TSMC
Density
23.5M / mm²
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
6.7
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
Motherboard Dependent
4x DisplayPort 1.4a
Bus Interface
IGP
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
GCN 3.0 IGP
Server Ampere
Successor
Vega II IGP
Server Hopper