aboutsummaryrefslogtreecommitdiff
path: root/gcc/d/expr.cc
diff options
context:
space:
mode:
authorTom de Vries <tdevries@suse.de>2022-02-18 16:50:03 +0100
committerTom de Vries <tdevries@suse.de>2022-02-19 19:57:12 +0100
commit8e5c34ab45f34aadea65c5ba33ec685264b6ec66 (patch)
tree7b409182fd796d391d64e4617cec639805ab5934 /gcc/d/expr.cc
parent9e3bbb4a8024121eb0fa675cb1f074218c1345a6 (diff)
downloadgcc-8e5c34ab45f34aadea65c5ba33ec685264b6ec66.zip
gcc-8e5c34ab45f34aadea65c5ba33ec685264b6ec66.tar.gz
gcc-8e5c34ab45f34aadea65c5ba33ec685264b6ec66.tar.bz2
[nvptx] Use nvptx_warpsync / nvptx_uniform_warp_check for -muniform-simt
With the default ptx isa 6.0, we have for uniform-simt-1.c: ... @%r33 atom.global.cas.b32 %r26, [a], %r28, %r29; shfl.sync.idx.b32 %r26, %r26, %r32, 31, 0xffffffff; ... The atomic insn is predicated by -muniform-simt, and the subsequent insn does a warp sync, at which point the warp is uniform again. But with -mptx=3.1, we have instead: ... @%r33 atom.global.cas.b32 %r26, [a], %r28, %r29; shfl.idx.b32 %r26, %r26, %r32, 31; ... The shfl does not sync the warp, and we want the warp to go back to executing uniformly asap. We cannot enforce this, but at least check this using nvptx_uniform_warp_check, similar to how that is done for openacc. Likewise, detect the case that no shfl insn is emitted, and add a nvptx_uniform_warp_check or nvptx_warpsync. gcc/ChangeLog: 2022-02-19 Tom de Vries <tdevries@suse.de> * config/nvptx/nvptx.cc (nvptx_unisimt_handle_set): Change return type to bool. (nvptx_reorg_uniform_simt): Insert nvptx_uniform_warp_check or nvptx_warpsync, if necessary. gcc/testsuite/ChangeLog: 2022-02-19 Tom de Vries <tdevries@suse.de> * gcc.target/nvptx/uniform-simt-1.c: Add scan-assembler test. * gcc.target/nvptx/uniform-simt-2.c: New test.
Diffstat (limited to 'gcc/d/expr.cc')
0 files changed, 0 insertions, 0 deletions