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
RTX A5000
CORE STATE
GA102
VRAM
24 GB
CLOCK SPEED
1695 MHz
TDP
230 W
BUS WIDTH
384 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
3dmark_3dmark_steel_nomad_dx12
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
Vega 3
RTX A5000
Core Specs
Shading Units
192
8,192
+4166.7%
Shaders
192
8,192
+4166.7%
TMUs
12
256
+2033.3%
ROPs
4
96
+2300.0%
Compute Units
3
—
SM Count
—
64
Clocks
Base Clock
300 MHz
1170 MHz
Boost Clock
1100 MHz
1695 MHz
Memory Clock
System Shared
2000 MHz
16 Gbps effective
Memory
Memory Size
System Shared
24 GB
VRAM (MB)
—
24,576
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
384 bit
Bandwidth
System Dependent
768.0 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
—
6 MB
Performance
Pixel Rate
4.400 GPixel/s
162.7 GPixel/s
Texture Rate
13.20 GTexel/s
433.9 GTexel/s
FP32 (TFLOPS)
422.4 GFLOPS
27.77 TFLOPS
FP64 (TFLOPS)
26.40 GFLOPS (1:16)
433.9 GFLOPS (1:64)
FP16 (TFLOPS)
844.8 GFLOPS (2:1)
27.77 TFLOPS (1:1)
AI/RT
RT Cores
—
64
Tensor Cores
—
256
Power
TDP
15 W
230 W
TDP (W)
15
230
+1433.3%
Suggested PSU
—
550 W
Power Connectors
None
1x 8-pin
Architecture
Architecture
GCN 5.0
Ampere
GPU Name
Picasso
GA102
Generation
Vega IGP
(Picasso)
Workstation Ampere
(Ax000)
Process Size
12 nm
8 nm
Transistors
4,940 million
28,300 million
Die Size
210 mm²
628 mm²
Foundry
GlobalFoundries
Samsung
Density
23.5M / mm²
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
6.7
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
112 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
Quadro Turing
Successor
Vega II IGP
Workstation Ada