AMD Radeon Pro 580 vs AMD Radeon HD 8990 OEM

Comparative analysis of AMD Radeon Pro 580 and AMD Radeon HD 8990 OEM videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

 

Differences

Reasons to consider the AMD Radeon Pro 580

  • Videocard is newer: launch date 4 year(s) 1 month(s) later
  • Around 16% higher core clock speed: 1100 MHz vs 950 MHz
  • Around 20% higher boost clock speed: 1200 MHz vs 1000 MHz
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 14 nm vs 28 nm
  • 2.5x lower typical power consumption: 150 Watt vs 375 Watt
  • Around 33% higher maximum memory size: 8 GB vs 2x 3 GB
  • Around 13% higher memory clock speed: 6780 MHz vs 6000 MHz
  • Around 49% better performance in PassMark - G3D Mark: 7753 vs 5214
  • Around 43% better performance in PassMark - G2D Mark: 943 vs 658
  • 2.5x better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 109.521 vs 44.481
  • Around 16% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 9.88 vs 8.536
  • Around 9% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 511.984 vs 470.237
Specifications (specs)
Launch date 5 June 2017 vs 24 April 2013
Core clock speed 1100 MHz vs 950 MHz
Boost clock speed 1200 MHz vs 1000 MHz
Manufacturing process technology 14 nm vs 28 nm
Thermal Design Power (TDP) 150 Watt vs 375 Watt
Maximum memory size 8 GB vs 2x 3 GB
Memory clock speed 6780 MHz vs 6000 MHz
Benchmarks
PassMark - G3D Mark 7753 vs 5214
PassMark - G2D Mark 943 vs 658
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 109.521 vs 44.481
CompuBench 1.5 Desktop - T-Rex (Frames/s) 9.88 vs 8.536
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 511.984 vs 470.237

Reasons to consider the AMD Radeon HD 8990 OEM

  • 11x more texture fill rate: 2x 128.0 GTexel / s billion / sec vs 193.0 GTexel / s
  • Around 78% higher pipelines: 2x 2048 vs 2304
  • Around 33% better floating-point performance: 2x 4,096 gflops vs 6,175 gflops
  • Around 64% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1984.655 vs 1206.829
  • Around 6% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 125.504 vs 117.944
Specifications (specs)
Texture fill rate 2x 128.0 GTexel / s billion / sec vs 193.0 GTexel / s
Pipelines 2x 2048 vs 2304
Floating-point performance 2x 4,096 gflops vs 6,175 gflops
Benchmarks
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 1984.655 vs 1206.829
CompuBench 1.5 Desktop - Video Composition (Frames/s) 125.504 vs 117.944

Compare benchmarks

GPU 1: AMD Radeon Pro 580
GPU 2: AMD Radeon HD 8990 OEM

PassMark - G3D Mark
GPU 1
GPU 2
7753
5214
PassMark - G2D Mark
GPU 1
GPU 2
943
658
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
109.521
44.481
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)
GPU 1
GPU 2
1206.829
1984.655
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
9.88
8.536
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
117.944
125.504
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
511.984
470.237
Name AMD Radeon Pro 580 AMD Radeon HD 8990 OEM
PassMark - G3D Mark 7753 5214
PassMark - G2D Mark 943 658
Geekbench - OpenCL 40271
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 109.521 44.481
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 1206.829 1984.655
CompuBench 1.5 Desktop - T-Rex (Frames/s) 9.88 8.536
CompuBench 1.5 Desktop - Video Composition (Frames/s) 117.944 125.504
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 511.984 470.237
GFXBench 4.0 - Car Chase Offscreen (Frames) 10113
GFXBench 4.0 - Manhattan (Frames) 2900
GFXBench 4.0 - T-Rex (Frames) 3353
GFXBench 4.0 - Car Chase Offscreen (Fps) 10113
GFXBench 4.0 - Manhattan (Fps) 2900
GFXBench 4.0 - T-Rex (Fps) 3353

Compare specifications (specs)

AMD Radeon Pro 580 AMD Radeon HD 8990 OEM

Essentials

Architecture GCN 4.0 GCN 1.0
Code name Polaris 20 Malta
Launch date 5 June 2017 24 April 2013
Place in performance rating 330 332
Type Workstation Desktop
Launch price (MSRP) $999

Technical info

Boost clock speed 1200 MHz 1000 MHz
Core clock speed 1100 MHz 950 MHz
Floating-point performance 6,175 gflops 2x 4,096 gflops
Manufacturing process technology 14 nm 28 nm
Pipelines 2304 2x 2048
Texture fill rate 193.0 GTexel / s 2x 128.0 GTexel / s billion / sec
Thermal Design Power (TDP) 150 Watt 375 Watt
Transistor count 5,700 million 4,313 million

Video outputs and ports

Display Connectors No outputs 1x DVI, 4x mini-DisplayPort

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 PCIe 3.0 x16
Length 241 mm 307 mm
Supplementary power connectors None

API support

DirectX 12.0 (12_0) 12.0 (11_1)
OpenGL 4.5 4.5

Memory

Maximum RAM amount 8 GB 2x 3 GB
Memory bandwidth 256.0 GB / s 2x 288.0 GB / s
Memory bus width 256 Bit 2x 384 Bit
Memory clock speed 6780 MHz 6000 MHz
Memory type GDDR5 GDDR5