Skip to Content.
Sympa Menu

cgal-discuss - [cgal-discuss] Polyhedron & OpenCL , mesh processing algorithm

Subject: CGAL users discussion list

List archive

[cgal-discuss] Polyhedron & OpenCL , mesh processing algorithm


Chronological Thread 
  • From: Mohamed Yousef <>
  • To:
  • Subject: [cgal-discuss] Polyhedron & OpenCL , mesh processing algorithm
  • Date: Mon, 8 Feb 2010 15:00:30 +0200
  • Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:content-type; b=Awa0FxfAIi/L+9o0azOb+Mvvm250t4nsL+EYYRx3GO4kMIITCpM8G4A5UmOYVCAiuv 5x1E0imoBXkq3u9pYbVwwfVDSbb5GEOd4Z26BJaFo+MXCeLoljBCa5IpgOzS88jui4D0 5Thi+4+UEeHiUT0o6QSN2qYzusXpRg4Wc1BHo=

Hello all,

I'm in the process of writing mesh processing algorithms that benefit from
OpenCL
the problem is that , in order to process vertices they have to be copied to
gpu , in random access array form
so the only option i can see is first to extract vertex information from the
half-edge , copy them into array , modify them in gpu , overwrite the
halfe-edge point values

but this is really too much overhead and memory usage problem , any one has
a better idea for the process or tackled OpenCL and CGAL before ?

Thanks



Archive powered by MHonArc 2.6.16.

Top of Page