KonstantinSeurer
/
mesa
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

nir/opt_intrinsics: Fix values for gl_SubGroupG{e,t}MaskARB 

Previously the values were calculated by just shifting ~0 by the
invocation ID. This would end up including bits that are higher than
gl_SubGroupSizeARB. The corresponding CTS test effectively requires that
these high bits be zero so it was failing. There is a Piglit test as
well but this appears to checking the wrong values so it passes.

For the two greater-than bitmasks, this patch adds an extra mask with
(~0>>(64-gl_SubGroupSizeARB)) to force these bits to zero.

Fixes: KHR-GL45.shader_ballot_tests.ShaderBallotBitmasks

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102680#c3
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Neil Roberts <nroberts@igalia.com>
This commit is contained in:
Neil Roberts 2017-10-31 15:05:33 +01:00
parent 9e849eb8bb
commit b697ece10a
1 changed files with 22 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/compiler/nir/nir_opt_intrinsics.c
View File

@ -28,6 +28,26 @@
* \file nir_opt_intrinsics.c
*/
static nir_ssa_def *
high_subgroup_mask(nir_builder *b,
nir_ssa_def *count,
uint64_t base_mask)
{
/* group_mask could probably be calculated more efficiently but we want to
* be sure not to shift by 64 if the subgroup size is 64 because the GLSL
* shift operator is undefined in that case. In any case if we were worried
* about efficency this should probably be done further down because the
* subgroup size is likely to be known at compile time.
*/
nir_ssa_def *subgroup_size = nir_load_subgroup_size(b);
nir_ssa_def *all_bits = nir_imm_int64(b, ~0ull);
nir_ssa_def *shift = nir_isub(b, nir_imm_int(b, 64), subgroup_size);
nir_ssa_def *group_mask = nir_ushr(b, all_bits, shift);
nir_ssa_def *higher_bits = nir_ishl(b, nir_imm_int64(b, base_mask), count);
return nir_iand(b, higher_bits, group_mask);
}
static bool
opt_intrinsics_impl(nir_function_impl *impl)
{
@ -95,10 +115,10 @@ opt_intrinsics_impl(nir_function_impl *impl)
replacement = nir_ishl(&b, nir_imm_int64(&b, 1ull), count);
break;
case nir_intrinsic_load_subgroup_ge_mask:
replacement = nir_ishl(&b, nir_imm_int64(&b, ~0ull), count);
replacement = high_subgroup_mask(&b, count, ~0ull);
break;
case nir_intrinsic_load_subgroup_gt_mask:
replacement = nir_ishl(&b, nir_imm_int64(&b, ~1ull), count);
replacement = high_subgroup_mask(&b, count, ~1ull);
break;
case nir_intrinsic_load_subgroup_le_mask:
replacement = nir_inot(&b, nir_ishl(&b, nir_imm_int64(&b, ~1ull), count));