GPU Comparison

Intel
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
nm
PROCESS 6 nm
LAUNCH DATE 2023
VS
NVIDIA
GEFORCE

Rubin GPU

CORE STATE GR100
VRAM 288 GB
CLOCK SPEED 2267 MHz
TDP 2300 W
BUS WIDTH 16384 bit
ARCHITECTURE Rubin
nm
PROCESS 3 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,229
N/A
geekbench_opencl
91,657
N/A
geekbench_vulkan
79,381
N/A

DETAILED SPECIFICATIONS

SPECIFICATION
A580
Rubin GPU
Core Specs
Shading Units
3,072
28,672 +833.3%
Shaders
3,072
28,672 +833.3%
TMUs
192
896 +366.7%
ROPs
96
24 -75.0%
SM Count
224
Execution Units
384
Clocks
Base Clock
1700 MHz
700 MHz
Boost Clock
2000 MHz
2267 MHz
Memory Clock
2000 MHz 16 Gbps effective
2695 MHz 10.8 Gbps effective
Memory
Memory Size
8 GB
288 GB
VRAM (MB)
8,192
294,912 +3500.0%
Memory Type
GDDR6
HBM4
Memory Bus
256 bit
16384 bit
Bandwidth
512.0 GB/s
22.1 TB/s
Cache
L1 Cache
256 KB (per SM)
L2 Cache
8 MB
128 MB
Performance
Pixel Rate
192.0 GPixel/s
54.41 GPixel/s
Texture Rate
384.0 GTexel/s
2,031.2 GTexel/s
FP32 (TFLOPS)
12.29 TFLOPS
130.0 TFLOPS
FP64 (TFLOPS)
1.536 TFLOPS (1:8)
32.50 TFLOPS (1:4)
FP16 (TFLOPS)
24.58 TFLOPS (2:1)
260.0 TFLOPS (2:1)
AI/RT
RT Cores
24
Tensor Cores
896
XMX Cores
384
Power
TDP
175 W
2300 W
TDP (W)
175
2,300 +1214.3%
Suggested PSU
450 W
2700 W
Power Connectors
2x 8-pin
Architecture
Architecture
Xe-HPG
Rubin
GPU Name
DG2-512
GR100
Generation
Alchemist (Arc 5)
Server Rubin (Rxx)
Process Size
6 nm
3 nm
Transistors
21,700 million
336,000 million
Die Size
406 mm²
1456 mm²
Foundry
TSMC
TSMC
Density
53.4M / mm²
230.8M / mm²
API Support
DirectX
12 Ultimate (12_2)
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
3.0
CUDA
10.7
Shader Model
6.6
Physical
Slot Width
Dual-slot
SXM Module
Outputs
1x HDMI 2.13x DisplayPort 2.0
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 6.0 x16
Other
Production
Active
Active
Predecessor
Xe Graphics
Server Blackwell
Successor
Battlemage
View Arc A580 Details View Rubin GPU Details