From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@freedesktop.org Subject: [Bug 70779] OpenCL hangs with big kernels Date: Sun, 14 Feb 2016 11:41:38 +0000 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1150779364==" Return-path: Received: from culpepper.freedesktop.org (unknown [131.252.210.165]) by gabe.freedesktop.org (Postfix) with ESMTP id 5B2336E065 for ; Sun, 14 Feb 2016 03:41:38 -0800 (PST) In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============1150779364== Content-Type: multipart/alternative; boundary="14554500981.f3a59dA04.21365"; charset="UTF-8" --14554500981.f3a59dA04.21365 Date: Sun, 14 Feb 2016 11:41:38 +0000 MIME-Version: 1.0 Content-Type: text/plain https://bugs.freedesktop.org/show_bug.cgi?id=70779 --- Comment #5 from EoD --- Created attachment 121742 --> https://bugs.freedesktop.org/attachment.cgi?id=121742&action=edit dmesg after running the uint_add16() kernel (In reply to Hristo Venev from comment #4) > Here are two kernels that fail: > __kernel void uint_div(__global const uint *a, __global const uint *b, > __global uint *c){ > c[0]=a[0]/b[0]; > } > __kernel void uint_add16(__global const uint *a, __global const uint *b, > __global uint *c){ > for(uint i=0;i<16;i++) c[i]=a[i]+b[i]; > } I actually can confirm that the 2nd kernel does cause a GPU stall in the radeon driver (r600/Barts). It causes no problem with amdgpu (radeonsi/Tonga). I am using kernel 4.5.0-rc3, current llvm 3.8 branch and current mesa git. As I am not overly good with OpenCL, is this kernel somehow problematic? -- You are receiving this mail because: You are the assignee for the bug. --14554500981.f3a59dA04.21365 Date: Sun, 14 Feb 2016 11:41:38 +0000 MIME-Version: 1.0 Content-Type: text/html

Comment # 5 on bug 70779 from 
Created attachment 121742 [details]
dmesg after running the uint_add16() kernel

(In reply to Hristo Venev from comment #4)
> Here are two kernels that fail:
> __kernel void uint_div(__global const uint *a,  __global const uint *b,
> __global uint *c){
>     c[0]=a[0]/b[0];
> }
> __kernel void uint_add16(__global const uint *a,  __global const uint *b,
> __global uint *c){
>     for(uint i=0;i<16;i++) c[i]=a[i]+b[i];
> }

I actually can confirm that the 2nd kernel does cause a GPU stall in the radeon
driver (r600/Barts). It causes no problem with amdgpu (radeonsi/Tonga).

I am using kernel 4.5.0-rc3, current llvm 3.8 branch and current mesa git.

As I am not overly good with OpenCL, is this kernel somehow problematic?

You are receiving this mail because:
  • You are the assignee for the bug.
--14554500981.f3a59dA04.21365-- --===============1150779364== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVsCg== --===============1150779364==--