GPU Comparison
RADEON
AMD Radeon Pro 580X
CORE STATE
Ellesmere
VRAM
8 GB
CLOCK SPEED
1200 MHz
TDP
185 W
BUS WIDTH
256 bit
ARCHITECTURE
GCN 4.0
PROCESS
14 nm
LAUNCH DATE
2019
VS
RADEON
Radeon PRO W6400
CORE STATE
Navi 24
VRAM
4 GB
CLOCK SPEED
2321 MHz
TDP
50 W
BUS WIDTH
64 bit
ARCHITECTURE
RDNA 2.0
PROCESS
6 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Pro 580X
PRO W6400
Core Specs
Shading Units
2,304
768
-66.7%
Shaders
2,304
768
-66.7%
TMUs
144
48
-66.7%
ROPs
32
32
0.0%
Compute Units
36
12
-66.7%
Clocks
Base Clock
1100 MHz
2039 MHz
Boost Clock
1200 MHz
2321 MHz
Memory Clock
1710 MHz
6.8 Gbps effective
2000 MHz
16 Gbps effective
Memory
Memory Size
8 GB
4 GB
VRAM (MB)
8,192
4,096
-50.0%
Memory Type
GDDR5
GDDR6
Memory Bus
256 bit
64 bit
Bandwidth
218.9 GB/s
128.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB per Array
L2 Cache
2 MB
1024 KB
L3 Cache
—
8 MB
L0 Cache
—
32 KB per WGP
Performance
Pixel Rate
38.40 GPixel/s
74.27 GPixel/s
Texture Rate
172.8 GTexel/s
111.4 GTexel/s
FP32 (TFLOPS)
5.530 TFLOPS
3.565 TFLOPS
FP64 (TFLOPS)
345.6 GFLOPS (1:16)
222.8 GFLOPS (1:16)
FP16 (TFLOPS)
5.530 TFLOPS (1:1)
7.130 TFLOPS (2:1)
AI/RT
RT Cores
—
12
Power
TDP
185 W
50 W
TDP (W)
185
50
-73.0%
Suggested PSU
—
250 W
Power Connectors
—
None
Architecture
Architecture
GCN 4.0
RDNA 2.0
GPU Name
Ellesmere
Navi 24
Generation
Radeon Pro Mac
(500X Series)
Radeon Pro Navi
(Navi II Series)
Process Size
14 nm
6 nm
Transistors
5,700 million
5,400 million
Die Size
232 mm²
107 mm²
Foundry
GlobalFoundries
TSMC
Density
24.6M / mm²
50.5M / mm²
API Support
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
2.2
Shader Model
6.7
6.8
Physical
Slot Width
IGP
Single-slot
Outputs
2x HDMI 2.0b
2x DisplayPort 1.4a
Bus Interface
Apple MPX
PCIe 4.0 x4
Other
Production
End-of-life
End-of-life
Predecessor
—
Radeon Pro Vega