Difference between revisions of "Performance Test"

From Yade

Line 21: Line 21:
 
=== Performance of Parallel Collider ===
 
=== Performance of Parallel Collider ===
   
[[File:performance_v_scaling_gpu.jpg]]
+
[[File:performance_v_scaling_gpu.jpg|600px|thumb|center|Fig. 1: Scaling on Intel machine]]
   
  +
Fig. 1 shows how version2 (parallel collider) scales in relation to version1 on the Intel machine. Interesting to note that for simulations with less than 100000 particles the scaling is almost not depending on the number of threads and scaling is slightly bigger than one. For simulations with more than 100000 particles things are looking differently. Using the total number of cores on the machine is not recommended, -j12 (and probably -j14) scales better than -j16.
[[File:performance_v_scaling_amd.jpg]]
 
  +
 
[[File:performance_v_scaling_amd.jpg|600px|thumb|center|Fig. 2: Scaling on AMD machine]]
  +
  +
Fig. 2 shows how version2 (parallel collider) scales in relation to version1 on the AMD machine. Similar trend as in Fig. 1 can be observed. However, it seems that the Intel scales better for less than -j12.
   
 
=== Comparison AMD/Intel ===
 
=== Comparison AMD/Intel ===

Revision as of 08:04, 28 February 2014

Introduction

This page summarises some results for the performance test of YADE (yade --performance) on a multicore machines. It should give an idea on how good YADE scales.

Test 1

Two versions of YADE are compared to each other and two different machines are used. The test was conducted on the computing grid of the University of Newcastle by Klaus.

YADE versions:

  • version1 (trunk): 2014-01-25.git-22c2441
  • version2 (see [1]): 2014-02-24.git-b60d388

Machines:

  • AMD: AMD Opteron(tm) Processor 6282 SE (64 cores)
  • Intel: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz (16 cores)


[1] : https://lists.launchpad.net/yade-dev/msg10498.html


Performance of Parallel Collider

Fig. 1: Scaling on Intel machine

Fig. 1 shows how version2 (parallel collider) scales in relation to version1 on the Intel machine. Interesting to note that for simulations with less than 100000 particles the scaling is almost not depending on the number of threads and scaling is slightly bigger than one. For simulations with more than 100000 particles things are looking differently. Using the total number of cores on the machine is not recommended, -j12 (and probably -j14) scales better than -j16.

Fig. 2: Scaling on AMD machine

Fig. 2 shows how version2 (parallel collider) scales in relation to version1 on the AMD machine. Similar trend as in Fig. 1 can be observed. However, it seems that the Intel scales better for less than -j12.

Comparison AMD/Intel

Performance arch scaling 2014-01-25.git-22c2441.jpg

Performance arch scaling 2014-02-24.git-b60d388.jpg