https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
Tom de Vries changed:
What|Removed |Added
Resolution|--- |FIXED
Target Milestone|---
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
--- Comment #7 from CVS Commits ---
The master branch has been updated by Tom de Vries :
https://gcc.gnu.org/g:a624388b9546b066250be8baa118b7d50c403c25
commit r12-7765-ga624388b9546b066250be8baa118b7d50c403c25
Author: Tom de Vries
Date:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
--- Comment #6 from Tom de Vries ---
Created attachment 52593
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=52593=edit
Tentative patch
(In reply to Tom de Vries from comment #4)
> The patch I have works for target boards unix and
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
--- Comment #5 from CVS Commits ---
The master branch has been updated by Tom de Vries :
https://gcc.gnu.org/g:f07178ca3c1e5dff799fb5016bb3767571db3165
commit r12-7586-gf07178ca3c1e5dff799fb5016bb3767571db3165
Author: Tom de Vries
Date:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
--- Comment #4 from Tom de Vries ---
The patch I have works for target boards unix and unix/-foffload=-mptx=3.1, but
I run into the hang for --target_board=unix/-foffload=-misa=sm_75.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
--- Comment #3 from Tom de Vries ---
Created attachment 52584
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=52584=edit
Tentative patch
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
--- Comment #2 from Tom de Vries ---
Hmm, the atom insn sets a register that is not used anywhere. So the shuffle
communicating the result doesn't make much sense.
We can fix that by doing:
...
diff --git a/gcc/config/nvptx/nvptx.cc
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104783
--- Comment #1 from Tom de Vries ---
Hmm, I wonder if nvptx_reorg_uniform_simt should run inbetween SIMT_ENTER and
SIMT_EXIT.