![A Scenario to Software Developers for
ppOpen-AT
3
Executable Code with
Optimization Candidates
and AT Function
Software
Developer
Description of AT by Using
ppOpen-AT
Invocate dedicated
Preprocessor
Program with AT
Functions
Optimization
that cannot be
established by
compilers
■Automatic Generated
Functions
Optimization
Candidates
Performance Monitor
Parameter Search
Performance Modeling
#pragma oat install unroll (i,j,k) region start
#pragma oat varied (i,j,k) from 1 to 8
for(i = 0 ; i < n ; i++){
for(j = 0 ; j < n ; j++){
for(k = 0 ; k < n ; k++){
A[i][j]=A[i][j]+B[i][k]*C[k][j]; }}}
#pragma oat install unroll (i,j,k) region end
Description By Software Developer
Optimizations for Source Codes,
Computer Resource, Power Consumption](https://image.slidesharecdn.com/ppopen-at-fdm-ad-20140730-141216201014-conversion-gate01/85/Overview-of-ppOpen-AT-Static-for-ppOpen-APPL-FDM-ver-0-2-0-3-320.jpg)
![An Example of Seism_3D Simulation
West part earthquake inTottori prefecture in Japan
at year 2000. ([1], pp.14)
The region of 820km x 410km x 128 km is discretized with 0.4km.
NX x NY x NZ = 2050 x 1025 x 320 ≒ 6.4 : 3.2 : 1.
[1] T. Furumura,“Large-scale Parallel FDM Simulation for Seismic Waves and Strong Shaking”, Supercomputing News,
Information Technology Center,The University of Tokyo,Vol.11, Special Edition 1, 2009. In Japanese.
Figure : Seismic wave translations in west part earthquake in Tottori prefecture in Japan. (a)
Measured waves; (b) Simulation results; (Reference : [1] in pp.13)](https://image.slidesharecdn.com/ppopen-at-fdm-ad-20140730-141216201014-conversion-gate01/85/Overview-of-ppOpen-AT-Static-for-ppOpen-APPL-FDM-ver-0-2-0-7-320.jpg)
![Maximum AT Effect (Xeon Phi, 8 Nodes)
558
200
171
30 20 51
Speedup [%]](https://image.slidesharecdn.com/ppopen-at-fdm-ad-20140730-141216201014-conversion-gate01/85/Overview-of-ppOpen-AT-Static-for-ppOpen-APPL-FDM-ver-0-2-0-8-320.jpg)
![Maximum AT Effect (Ivy Bridge, 8 Nodes)
48
42
67
29
47
23
Speedup [%]](https://image.slidesharecdn.com/ppopen-at-fdm-ad-20140730-141216201014-conversion-gate01/85/Overview-of-ppOpen-AT-Static-for-ppOpen-APPL-FDM-ver-0-2-0-9-320.jpg)
![Maximum AT Effect (FX10, 8 Nodes)
10 9 7
37
46
2
Speedup [%]](https://image.slidesharecdn.com/ppopen-at-fdm-ad-20140730-141216201014-conversion-gate01/85/Overview-of-ppOpen-AT-Static-for-ppOpen-APPL-FDM-ver-0-2-0-10-320.jpg)
Overview of ppOpen-AT/Static for ppOpen-APPL/FDM ver. 0.2.0
- 1. Overview of ppOpen-AT/Static for ppOpen-APPL/FDM ver. 0.2.0 Takahiro Katagiri (Information Technology Center, The University of Tokyo) 1 As of July 30th, 2014
- 3. A Scenario to Software Developers for ppOpen-AT 3 Executable Code with Optimization Candidates and AT Function Software Developer Description of AT by Using ppOpen-AT Invocate dedicated Preprocessor Program with AT Functions Optimization that cannot be established by compilers ■Automatic Generated Functions Optimization Candidates Performance Monitor Parameter Search Performance Modeling #pragma oat install unroll (i,j,k) region start #pragma oat varied (i,j,k) from 1 to 8 for(i = 0 ; i < n ; i++){ for(j = 0 ; j < n ; j++){ for(k = 0 ; k < n ; k++){ A[i][j]=A[i][j]+B[i][k]*C[k][j]; }}} #pragma oat install unroll (i,j,k) region end Description By Software Developer Optimizations for Source Codes, Computer Resource, Power Consumption
- 4. Target Application Seism_3D: Simulation for seismic wave analysis. Developed by Professor Furumura at the University of Tokyo. ◦ The code is re-constructed as ppOpen-APPL/FDM. ◦ version 0.2.0 OMP parallelization is implemented. Finite Differential Method (FDM) 3D simulation ◦ 3D arrays are allocated. Data type: Single Precision (real*4) 4
- 5. Target Computation Kernels in Current Implementation 1. Kernel update_stress ◦ 8 Kinds of Candidates with Loop fusion and Loop Split. 2. Kernel update_vel ◦ 5 Kinds of Candidates with Loop Fusion and Loop Split, and reordering of statements. 3 Kinds of Candidates with Loop Fusion and Loop Split. 3. Kernel update_stress_sponge 4. Kernel update_vel_sponge 5. Kernel ppohFDM_pdiffx3_p4 6. Kernel ppohFDM_pdiffx3_m4 7. Kernel ppohFDM_pdiffy3_p4 8. Kernel ppohFDM_pdiffy3_m4 9. Kernel ppohFDM_pdiffz3_p4 10. Kernel ppohFDM_pdiffz3_m4 5
- 6. Additional Kernels in Next Release (Planned in Nov. 2014) 3 Kinds of Candidates with Loop Fusion and Loop Split for data packing and unpacking. 11. Kernel ppohFDM_ps_pack 12. Kernel ppohFDM_ps_unpack 13. Kernel ppohFDM_pv_pack 14. Kernel ppohFDM_pv_unpack 6
- 7. An Example of Seism_3D Simulation West part earthquake inTottori prefecture in Japan at year 2000. ([1], pp.14) The region of 820km x 410km x 128 km is discretized with 0.4km. NX x NY x NZ = 2050 x 1025 x 320 ≒ 6.4 : 3.2 : 1. [1] T. Furumura,“Large-scale Parallel FDM Simulation for Seismic Waves and Strong Shaking”, Supercomputing News, Information Technology Center,The University of Tokyo,Vol.11, Special Edition 1, 2009. In Japanese. Figure : Seismic wave translations in west part earthquake in Tottori prefecture in Japan. (a) Measured waves; (b) Simulation results; (Reference : [1] in pp.13)