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
H100 CNX
CORE STATE
GH100
VRAM
80 GB
CLOCK SPEED
1845 MHz
TDP
350 W
BUS WIDTH
5120 bit
ARCHITECTURE
Hopper
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
A580
H100 CNX
Core Specs
Shading Units
3,072
14,592
+375.0%
Shaders
3,072
14,592
+375.0%
TMUs
192
456
+137.5%
ROPs
96
24
-75.0%
SM Count
—
114
Execution Units
384
—
Clocks
Base Clock
1700 MHz
690 MHz
Boost Clock
2000 MHz
1845 MHz
Memory Clock
2000 MHz
16 Gbps effective
1593 MHz
3.2 Gbps effective
Memory
Memory Size
8 GB
80 GB
VRAM (MB)
8,192
81,920
+900.0%
Memory Type
GDDR6
HBM2e
Memory Bus
256 bit
5120 bit
Bandwidth
512.0 GB/s
2.04 TB/s
Cache
L1 Cache
—
256 KB (per SM)
L2 Cache
8 MB
50 MB
Performance
Pixel Rate
192.0 GPixel/s
44.28 GPixel/s
Texture Rate
384.0 GTexel/s
841.3 GTexel/s
FP32 (TFLOPS)
12.29 TFLOPS
53.84 TFLOPS
FP64 (TFLOPS)
1.536 TFLOPS (1:8)
26.92 TFLOPS (1:2)
FP16 (TFLOPS)
24.58 TFLOPS (2:1)
215.4 TFLOPS (4:1)
AI/RT
RT Cores
24
—
Tensor Cores
—
456
XMX Cores
384
—
Power
TDP
175 W
350 W
TDP (W)
175
350
+100.0%
Suggested PSU
450 W
750 W
Power Connectors
2x 8-pin
8-pin EPS
Architecture
Architecture
Xe-HPG
Hopper
GPU Name
DG2-512
GH100
Generation
Alchemist
(Arc 5)
Server Hopper
(Hxx)
Process Size
6 nm
5 nm
Transistors
21,700 million
80,000 million
Die Size
406 mm²
814 mm²
Foundry
TSMC
TSMC
Density
53.4M / mm²
98.3M / mm²
API Support
DirectX
12 Ultimate (12_2)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
3.0
3.0
CUDA
—
9.0
Shader Model
6.6
—
Physical
Slot Width
Dual-slot
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
1x HDMI 2.13x DisplayPort 2.0
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Other
Production
Active
Active
Predecessor
Xe Graphics
Server Ada
Successor
Battlemage
Server Blackwell