vasp 5 4 1
play

VASP 5.4.1 February 2017 Interface on P100s PCIe 0.00500 - PowerPoint PPT Presentation

Dec 03, 2023 •264 likes •451 views

VASP 5.4.1 February 2017 Interface on P100s PCIe 0.00500 Interface Running VASP version 5.4.1 0.00450 0.00434 The blue node contains Dual Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00400 2.5X (Broadwell) CPUs 0.00359 0.00350 2.1X

  1. VASP 5.4.1 February 2017

  2. Interface on P100s PCIe 0.00500 Interface Running VASP version 5.4.1 0.00450 0.00434 The blue node contains Dual Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00400 2.5X (Broadwell) CPUs 0.00359 0.00350 2.1X The green nodes contain Dual Intel 0.00308 Xeon E5-2699 v4@2.2GHz [3.6GHz 0.00300 1.8X Turbo] (Broadwell) CPUs + Tesla P100 1/seconds PCIe GPUs 0.00250 0.00228 ➢ 1x P100 PCIe is paired with Single 0.00200 1.3X 0.00171 Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] (Broadwell) 0.00150 0.00100 Interface between a platinum slab Pt(111) (108 atoms) and liquid water (120 water 0.00050 molecules) (468 ions) 0.00000 1256 bands 1 Broadwell node 1 node + 1 node + 1 node + 1 node + 762048 plane waves 1x P100 PCIe 2x P100 PCIe 4x P100 PCIe 8x P100 PCIe ALGO = Fast (Davidson + RMM-DIIS) per node per node per node per node 78

  3. Interface on P100s SXM2 0.00500 Interface Running VASP version 5.4.1 0.00462 0.00450 2.7X The blue node contains Dual Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00400 (Broadwell) CPUs 0.00350 0.00326 The green nodes contain Dual Intel Xeon E5-2698 v4@2.2GHz [3.6GHz 0.00300 1.9X 0.00270 Turbo] (Broadwell) CPUs + Tesla P100 1/seconds SXM2 GPUs 0.00250 0.00228 1.6X ➢ 1x P100 SXM2 is paired with Single 0.00200 1.3X 0.00171 Intel Xeon E5-2698 v4@2.2GHz [3.6GHz Turbo] (Broadwell) 0.00150 0.00100 Interface between a platinum slab Pt(111) (108 atoms) and liquid water (120 water 0.00050 molecules) (468 ions) 0.00000 1256 bands 1 Broadwell node 1 node + 1 node + 1 node + 1 node + 762048 plane waves 1x P100 SXM2 2x P100 SXM2 4x P100 SXM2 8x P100 SXM2 ALGO = Fast (Davidson + RMM-DIIS) per node per node per node per node 79

  4. Silica IFPEN on P100s PCIe 0.00800 Silica IFPEN Running VASP version 5.4.1 0.00674 0.00700 2.5X The blue node contains Dual Intel Xeon 0.00616 E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00600 (Broadwell) CPUs 2.3X 0.00500 0.00474 The green nodes contain Dual Intel 1/seconds Xeon E5-2699 v4@2.2GHz [3.6GHz 0.00380 Turbo] (Broadwell) CPUs + Tesla P100 0.00400 1.7X PCIe GPUs 0.00300 0.00273 1.4X ➢ 1x P100 PCIe is paired with Single Intel Xeon E5-2699 v4@2.2GHz 0.00200 [3.6GHz Turbo] (Broadwell) 0.00100 240 ions, cristobalite (high) bulk 720 bands 0.00000 ? plane waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + ALGO = Very Fast (RMM-DIIS) 1x P100 PCIe 2x P100 PCIe 4x P100 PCIe 8x P100 PCIe per node per node per node per node 80

  5. Silica IFPEN on P100s SXM2 0.00800 Silica IFPEN Running VASP version 5.4.1 0.00692 0.00700 2.5X The blue node contains Dual Intel Xeon 0.00616 E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00600 2.3X (Broadwell) CPUs 0.00475 0.00500 The green nodes contain Dual Intel 1/seconds Xeon E5-2698 v4@2.2GHz [3.6GHz Turbo] (Broadwell) CPUs + Tesla P100 0.00400 0.00352 1.7X SXM2 GPUs 0.00300 0.00273 1.3X ➢ 1x P100 SXM2 is paired with Single Intel Xeon E5-2698 v4@2.2GHz 0.00200 [3.6GHz Turbo] (Broadwell) 0.00100 240 ions, cristobalite (high) bulk 720 bands 0.00000 ? plane waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + ALGO = Very Fast (RMM-DIIS) 1x P100 SXM2 2x P100 SXM2 4x P100 SXM2 8x P100 SXM2 per node per node per node per node 81

  6. Si-Huge on P100s PCIe 0.00080 Si-Huge 0.00074 Running VASP version 5.4.1 0.00070 3.9X The blue node contains Dual Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00058 0.00060 (Broadwell) CPUs 0.00050 The green nodes contain Dual Intel 3.1X 1/seconds 0.00044 Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] (Broadwell) CPUs + Tesla P100 0.00040 2.3X 0.00034 PCIe GPUs 0.00030 1.8X 1x P100 PCIe is paired with Single ➢ Intel Xeon E5-2699 v4@2.2GHz 0.00019 0.00020 [3.6GHz Turbo] (Broadwell) 0.00010 512 Si atoms 1282 bands 0.00000 864000 Plane Waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + Algo = Normal (blocked Davidson) 1x P100 PCIe 2x P100 PCIe 4x P100 PCIe 8x P100 PCIe per node per node per node per node 82

  7. Si-Huge on P100s SXM2 0.00070 Si-Huge 0.00066 Running VASP version 5.4.1 0.00060 3.5X The blue node contains Dual Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] (Broadwell) CPUs 0.00050 0.00045 The green nodes contain Dual Intel 0.00040 0.00040 2.4X Xeon E5-2698 v4@2.2GHz [3.6GHz 1/seconds 2.1X Turbo] (Broadwell) CPUs + Tesla P100 0.00033 SXM2 GPUs 0.00030 1.7X 1x P100 SXM2 is paired with Single ➢ 0.00019 Intel Xeon E5-2698 v4@2.2GHz 0.00020 [3.6GHz Turbo] (Broadwell) 0.00010 512 Si atoms 1282 bands 0.00000 864000 Plane Waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + Algo = Normal (blocked Davidson) 1x P100 SXM2 2x P100 SXM2 4x P100 SXM2 8x P100 SXM2 per node per node per node per node 83

  8. SupportedSystems on P100s PCIe 0.01000 SupportedSystems Running VASP version 5.4.1 0.00796 0.00794 The blue node contains Dual Intel Xeon 0.00800 E5-2699 v4@2.2GHz [3.6GHz Turbo] (Broadwell) CPUs 1.9X 1.9X 0.00651 The green nodes contain Dual Intel 0.00600 Xeon E5-2699 v4@2.2GHz [3.6GHz 1/seconds 0.00518 1.6X Turbo] (Broadwell) CPUs + Tesla P100 PCIe GPUs 0.00413 0.00400 ➢ 1x P100 PCIe is paired with Single 1.3X Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] (Broadwell) 0.00200 267 ions 788 bands 0.00000 762048 plane waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + ALGO = Fast (Davidson + RMM-DIIS) 1x P100 PCIe 2x P100 PCIe 4x P100 PCIe 8x P100 PCIe per node per node per node per node 84

  9. SupportedSystems on P100s SXM2 0.01000 SupportedSystems 0.00938 Running VASP version 5.4.1 0.00900 2.3X The blue node contains Dual Intel Xeon 0.00800 E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00692 (Broadwell) CPUs 0.00700 The green nodes contain Dual Intel 0.00570 0.00600 1.7X Xeon E5-2698 v4@2.2GHz [3.6GHz 1/seconds 0.00516 Turbo] (Broadwell) CPUs + Tesla P100 0.00500 1.4X SXM2 GPUs 0.00413 0.00400 1.2X ➢ 1x P100 SXM2 is paired with Single 0.00300 Intel Xeon E5-2698 v4@2.2GHz [3.6GHz Turbo] (Broadwell) 0.00200 0.00100 267 ions 788 bands 0.00000 762048 plane waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + ALGO = Fast (Davidson + RMM-DIIS) 1x P100 SXM2 2x P100 SXM2 4x P100 SXM2 8x P100 SXM2 per node per node per node per node 85

  10. NiAl-MD on P100s PCIe 0.01000 NiAl-MD 0.00936 0.00902 Running VASP version 5.4.1 0.00900 2.7X The blue node contains Dual Intel Xeon 0.00800 2.6X E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.00731 (Broadwell) CPUs 0.00700 2.1X The green nodes contain Dual Intel 0.00577 0.00600 Xeon E5-2699 v4@2.2GHz [3.6GHz 1/seconds Turbo] (Broadwell) CPUs + Tesla P100 0.00500 1.7X PCIe GPUs 0.00400 0.00347 ➢ 1x P100 PCIe is paired with Single 0.00300 Intel Xeon E5-2699 v4@2.2GHz [3.6GHz Turbo] (Broadwell) 0.00200 0.00100 500 ions 3200 bands 0.00000 729000 plane waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + ALGO = Fast (Davidson + RMM-DIIS) 1x P100 PCIe 2x P100 PCIe 4x P100 PCIe 8x P100 PCIe per node per node per node per node 86

  11. NiAl-MD on P100s SXM2 0.0100 NiAl-MD 0.0090 Running VASP version 5.4.1 0.0090 2.6X 0.0081 The blue node contains Dual Intel Xeon 0.0080 2.3X E5-2699 v4@2.2GHz [3.6GHz Turbo] 0.0074 (Broadwell) CPUs 0.0070 2.1X The green nodes contain Dual Intel 0.0057 0.0060 Xeon E5-2698 v4@2.2GHz [3.6GHz 1/seconds Turbo] (Broadwell) CPUs + Tesla P100 0.0050 1.6X SXM2 GPUs 0.0040 0.0035 ➢ 1x P100 SXM2 is paired with Single 0.0030 Intel Xeon E5-2698 v4@2.2GHz [3.6GHz Turbo] (Broadwell) 0.0020 0.0010 500 ions 3200 bands 0.0000 729000 plane waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + ALGO = Fast (Davidson + RMM-DIIS) 1x P100 SXM2 2x P100 SXM2 4x P100 SXM2 8x P100 SXM2 per node per node per node per node 87

  12. LiZnO on P100s PCIe 0.00180 LiZnO 0.00160 0.00153 Running VASP version 5.4.1 0.00137 0.00140 1.4X The blue node contains Dual Intel Xeon 0.00120 E5-2699 v4@2.2GHz [3.6GHz Turbo] 1.3X 0.00106 (Broadwell) CPUs 1/seconds 0.00100 The green nodes contain Dual Intel Xeon E5-2699 v4@2.2GHz [3.6GHz 0.00080 Turbo] (Broadwell) CPUs + Tesla P100 PCIe GPUs 0.00060 0.00040 500 ions 3200 bands 0.00020 729000 plane waves ALGO = Fast (Davidson + RMM-DIIS) 0.00000 1 Broadwell node 1 node + 1 node + 2x P100 PCIe 4x P100 PCIe per node per node 88

  13. LiZnO on P100s SXM2 0.0020 LiZnO Running VASP version 5.4.1 0.0018 0.0018 The blue node contains Dual Intel Xeon 0.0016 0.0015 1.6X E5-2699 v4@2.2GHz [3.6GHz Turbo] (Broadwell) CPUs 0.0013 0.0014 1.4X The green nodes contain Dual Intel 0.0012 0.0011 1.2X 0.0011 Xeon E5-2698 v4@2.2GHz [3.6GHz 1/seconds Turbo] (Broadwell) CPUs + Tesla P100 0.0010 1.0X SXM2 GPUs 0.0008 ➢ 1x P100 SXM2 is paired with Single 0.0006 Intel Xeon E5-2698 v4@2.2GHz [3.6GHz Turbo] (Broadwell) 0.0004 0.0002 500 ions 3200 bands 0.0000 729000 plane waves 1 Broadwell node 1 node + 1 node + 1 node + 1 node + ALGO = Fast (Davidson + RMM-DIIS) 1x P100 PCIe 2x P100 PCIe 4x P100 PCIe 8x P100 PCIe per node per node per node per node 89

Recommend

NEW GPU FUNCTIONALITY IN VASP WITH OPENACC AND CUDA LIBRARIES Stefan Maintz, 2019/12/18 AGENDA

NEW GPU FUNCTIONALITY IN VASP WITH OPENACC AND CUDA LIBRARIES Stefan Maintz, 2019/12/18 AGENDA

NEW GPU FUNCTIONALITY IN VASP WITH OPENACC AND CUDA LIBRARIES Stefan Maintz, 2019/12/18 AGENDA Introduction to VASP GPU Acceleration in VASP 5 Prioritizing Use Cases for New Porting Efforts OpenACC in VASP 6 and Supported Features

705 views • 42 slides
PORTING VASP TO GPUS WITH OPENACC Stefan Maintz, Dr. Markus Wetzstein 03/26/2018

PORTING VASP TO GPUS WITH OPENACC Stefan Maintz, Dr. Markus Wetzstein 03/26/2018

PORTING VASP TO GPUS WITH OPENACC Stefan Maintz, Dr. Markus Wetzstein 03/26/2018 smaintz@nvidia.com; mwetzstein@nvidia.com Short introduction to VASP Status of the CUDA port Prioritizing Use Cases for GPU Acceleration AGENDA OpenACC in VASP

776 views • 41 slides
VASP 5.4.4 October 2017 Silica IFPEN on V100s PCIe 0.00700 0.00628 0.00600 (Untuned on Volta)

VASP 5.4.4 October 2017 Silica IFPEN on V100s PCIe 0.00700 0.00628 0.00600 (Untuned on Volta)

VASP 5.4.4 October 2017 Silica IFPEN on V100s PCIe 0.00700 0.00628 0.00600 (Untuned on Volta) 3.0X 0.00537 Running VASP version 5.4.4 0.00500 The blue node contains Dual Intel Xeon 2.6X E5-2690 v4@2.6GHz [3.5GHz Turbo] 0.00418

402 views • 13 slides
VASP Project Briefing Report Eastern Alliance for Greenhouse Action Northern Alliance for

VASP Project Briefing Report Eastern Alliance for Greenhouse Action Northern Alliance for

Future Assets Forum VASP Project Briefing Report Eastern Alliance for Greenhouse Action Northern Alliance for Greenhouse Action December 2015 Future Assets Forum Workshop 1 Dr Gerard Healey and Aaron Yuen 22 nd October 2015 Activity 1: What

588 views • 26 slides
Type III Secretion System 1 Pedestal Formation Cytoskeletal Proteins Recruited Tip: active in

Type III Secretion System 1 Pedestal Formation Cytoskeletal Proteins Recruited Tip: active in

Type III Secretion System 1 Pedestal Formation Cytoskeletal Proteins Recruited Tip: active in pedestal formation Tir, N-WASP, -actinin, Arp2/3, gelsolin, talin, VASP, Nck, CD44 Length: structural components -actinin, Arp2/3, talin,

512 views • 47 slides

More recommend