GPU Comparison

AMD
RADEON

AMD Radeon Pro 580

CORE STATE Ellesmere
VRAM 8 GB
CLOCK SPEED 1200 MHz
TDP 185 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 4.0
nm
PROCESS 14 nm
LAUNCH DATE 2017
VS
NVIDIA
GEFORCE

B200

CORE STATE GB100
VRAM 90 GB
CLOCK SPEED 1965 MHz
TDP 1000 W
BUS WIDTH 4096 bit
ARCHITECTURE Blackwell
nm
PROCESS 5 nm
LAUNCH DATE

PERFORMANCE BENCHMARKS

geekbench_metal
39,264
N/A
geekbench_opencl
38,457
345,482
geekbench_vulkan
43,285
N/A

DETAILED SPECIFICATIONS

SPECIFICATION
Pro 580
B200
Core Specs
Shading Units
2,304
18,944 +722.2%
Shaders
2,304
18,944 +722.2%
TMUs
144
592 +311.1%
ROPs
32
24 -25.0%
Compute Units
36
SM Count
148
Clocks
Base Clock
1100 MHz
700 MHz
Boost Clock
1200 MHz
1965 MHz
Memory Clock
1695 MHz 6.8 Gbps effective
2000 MHz 8 Gbps effective
Memory
Memory Size
8 GB
90 GB
VRAM (MB)
8,192
92,160 +1025.0%
Memory Type
GDDR5
HBM3e
Memory Bus
256 bit
4096 bit
Bandwidth
217.0 GB/s
4.10 TB/s
Cache
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
2 MB
50 MB
Performance
Pixel Rate
38.40 GPixel/s
47.16 GPixel/s
Texture Rate
172.8 GTexel/s
1,163.3 GTexel/s
FP32 (TFLOPS)
5.530 TFLOPS
74.45 TFLOPS
FP64 (TFLOPS)
345.6 GFLOPS (1:16)
37.22 TFLOPS (1:2)
FP16 (TFLOPS)
5.530 TFLOPS (1:1)
1,191.2 TFLOPS (16:1)
AI/RT
Tensor Cores
592
Power
TDP
185 W
1000 W
TDP (W)
185
1,000 +440.5%
Suggested PSU
1400 W
Power Connectors
None
Architecture
Architecture
GCN 4.0
Blackwell
GPU Name
Ellesmere
GB100
Generation
Radeon Pro Mac (500 Series)
Server Blackwell (Bxx)
Process Size
14 nm
5 nm
Transistors
5,700 million
104,000 million
Die Size
232 mm²
Foundry
GlobalFoundries
TSMC
Density
24.6M / mm²
API Support
DirectX
12 (12_0)
OpenGL
4.6
Vulkan
1.3
OpenCL
2.1
3.0
CUDA
10.0
Shader Model
6.7
Physical
Slot Width
IGP
SXM Module
Outputs
Portable Device Dependent
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
Server Hopper
Successor
Server Rubin
View Radeon Pro 580 Details View B200 Details