diff options
| author | Tom de Vries <tdevries@suse.de> | 2022-03-07 15:57:11 +0100 |
|---|---|---|
| committer | Tom de Vries <tdevries@suse.de> | 2022-03-10 12:19:48 +0100 |
| commit | 3e743d654b3598d54b3c2eb837a48baeac00a543 (patch) | |
| tree | 337af04dfe31f915582c85938f944a65eb97ea23 /gcc | |
| parent | 3ebcc053a4bd32973762b671b444730baf558805 (diff) | |
| download | gcc-3e743d654b3598d54b3c2eb837a48baeac00a543.zip gcc-3e743d654b3598d54b3c2eb837a48baeac00a543.tar.gz gcc-3e743d654b3598d54b3c2eb837a48baeac00a543.tar.bz2 | |
[nvptx] Handle unused result in nvptx_unisimt_handle_set
For an example:
...
#pragma omp target map(tofrom: counter_N0)
#pragma omp simd
for (int i = 0 ; i < 1 ; i++ )
{
#pragma omp atomic update
counter_N0 = counter_N0 + 1 ;
}
...
I noticed that the result of the atomic update (%r30) is propagated:
...
@%r33 atom.add.u32 _, [%r29], 1;
shfl.sync.idx.b32 %r30, %r30, %r32, 31, 0xffffffff;
...
even though it is unused (which is why the bit bucket operand _ is used).
Fix this by not emitting the shuffle in this case, such that we have instead:
...
@%r33 atom.add.u32 _, [%r29], 1;
bar.warp.sync 0xffffffff;
...
Tested on nvptx.
gcc/ChangeLog:
2022-03-07 Tom de Vries <tdevries@suse.de>
* config/nvptx/nvptx.cc (nvptx_unisimt_handle_set): Handle unused
result.
gcc/testsuite/ChangeLog:
2022-03-07 Tom de Vries <tdevries@suse.de>
* gcc.target/nvptx/uniform-simt-4.c: New test.
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/config/nvptx/nvptx.cc | 4 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.target/nvptx/uniform-simt-4.c | 22 |
2 files changed, 25 insertions, 1 deletions
diff --git a/gcc/config/nvptx/nvptx.cc b/gcc/config/nvptx/nvptx.cc index 14911bd..c41e305 100644 --- a/gcc/config/nvptx/nvptx.cc +++ b/gcc/config/nvptx/nvptx.cc @@ -3274,7 +3274,9 @@ static bool nvptx_unisimt_handle_set (rtx set, rtx_insn *insn, rtx master) { rtx reg; - if (GET_CODE (set) == SET && REG_P (reg = SET_DEST (set))) + if (GET_CODE (set) == SET + && REG_P (reg = SET_DEST (set)) + && find_reg_note (insn, REG_UNUSED, reg) == NULL_RTX) { emit_insn_after (nvptx_gen_shuffle (reg, reg, master, SHUFFLE_IDX), insn); diff --git a/gcc/testsuite/gcc.target/nvptx/uniform-simt-4.c b/gcc/testsuite/gcc.target/nvptx/uniform-simt-4.c new file mode 100644 index 0000000..c33de7a --- /dev/null +++ b/gcc/testsuite/gcc.target/nvptx/uniform-simt-4.c @@ -0,0 +1,22 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -muniform-simt -mptx=_" } */ + +enum memmodel +{ + MEMMODEL_RELAXED = 0 +}; + +unsigned long long int *p64; +unsigned long long int v64; + +int +main() +{ + __atomic_fetch_add (p64, v64, MEMMODEL_RELAXED); + + return 0; +} + +/* { dg-final { scan-assembler-times "atom.add.u64\[\t \]+_," 1 } } */ +/* { dg-final { scan-assembler-times "bar.warp.sync" 1 } } */ +/* { dg-final { scan-assembler-not "shfl.sync.idx" } } */ |