GPU Comparison
GPU
Intel Arc A580
CORE STATE
DG2-512
VRAM
8 GB
CLOCK SPEED
2000 MHz
TDP
175 W
BUS WIDTH
256 bit
ARCHITECTURE
Xe-HPG
PROCESS
6 nm
LAUNCH DATE
2023
VS
GEFORCE
Quadro K620
CORE STATE
GM107
VRAM
2 GB
CLOCK SPEED
1124 MHz
TDP
45 W
BUS WIDTH
128 bit
ARCHITECTURE
Maxwell
PROCESS
28 nm
LAUNCH DATE
2014
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
A580
Quadro K620
Core Specs
Shading Units
3,072
384
-87.5%
Shaders
3,072
384
-87.5%
TMUs
192
24
-87.5%
ROPs
96
16
-83.3%
Execution Units
384
—
Clocks
Base Clock
1700 MHz
1058 MHz
Boost Clock
2000 MHz
1124 MHz
Memory Clock
2000 MHz
16 Gbps effective
900 MHz
1800 Mbps effective
Memory
Memory Size
8 GB
2 GB
VRAM (MB)
8,192
2,048
-75.0%
Memory Type
GDDR6
DDR3
Memory Bus
256 bit
128 bit
Bandwidth
512.0 GB/s
28.80 GB/s
Cache
L1 Cache
—
64 KB (per SMM)
L2 Cache
8 MB
2 MB
Performance
Pixel Rate
192.0 GPixel/s
17.98 GPixel/s
Texture Rate
384.0 GTexel/s
26.98 GTexel/s
FP32 (TFLOPS)
12.29 TFLOPS
863.2 GFLOPS
FP64 (TFLOPS)
1.536 TFLOPS (1:8)
26.98 GFLOPS (1:32)
FP16 (TFLOPS)
24.58 TFLOPS (2:1)
—
AI/RT
RT Cores
24
—
XMX Cores
384
—
Power
TDP
175 W
45 W
TDP (W)
175
45
-74.3%
Suggested PSU
450 W
200 W
Power Connectors
2x 8-pin
None
Architecture
Architecture
Xe-HPG
Maxwell
GPU Name
DG2-512
GM107
Generation
Alchemist
(Arc 5)
Quadro Kepler
(Kx200)
Process Size
6 nm
28 nm
Transistors
21,700 million
1,870 million
Die Size
406 mm²
148 mm²
Foundry
TSMC
TSMC
Density
53.4M / mm²
12.6M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
—
5.0
Shader Model
6.6
6.7 (5.1)
Physical
Slot Width
Dual-slot
Single-slot
Length
—
160 mm
6.3 inches
Height
—
69 mm
2.7 inches
Outputs
1x HDMI 2.13x DisplayPort 2.0
1x DVI1x DisplayPort 1.2
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16
Other
Production
Active
End-of-life
Predecessor
Xe Graphics
Quadro Fermi
Successor
Battlemage
Quadro Maxwell