From 4a79f2be337cef920fc8ea5048fabc106bac492e Mon Sep 17 00:00:00 2001 From: Ilia Mirkin Date: Sat, 24 Jun 2017 18:35:29 -0400 Subject: nv50/ir: fix combineLd/St to update existing records as necessary Previously the logic would decide that the record is kept, which translates into keep = false in the caller, which meant that these passes did not run. While it's right that keep = false which means that a new record does not need to be added, we do still have to perform the usual list maintenance. It's easiest to do this pre-merge rather than post. The lowering that clip/cull distance passes produce triggers this bug in TCS (since reading outputs is done differently in other stages), but it should be possible to achieve it with the right sequence of regular reads/writes. Fixes: KHR-GL45.cull_distance.functional Fixes: generated_tests/spec/arb_tessellation_shader/execution/tes-input/tes-input-gl_ClipDistance.shader_test Signed-off-by: Ilia Mirkin Reviewed-by: Samuel Pitoiset Cc: mesa-stable@lists.freedesktop.org --- src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'src/gallium') diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp index 7c4420682a7..df83f18ae83 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp @@ -2486,6 +2486,10 @@ MemoryOpt::combineLd(Record *rec, Instruction *ld) assert(sizeRc + sizeLd <= 16 && offRc != offLd); + // lock any stores that overlap with the load being merged into the + // existing record. + lockStores(ld); + for (j = 0; sizeRc; sizeRc -= rec->insn->getDef(j)->reg.size, ++j); if (offLd < offRc) { @@ -2542,6 +2546,10 @@ MemoryOpt::combineSt(Record *rec, Instruction *st) if (prog->getType() == Program::TYPE_COMPUTE && rec->rel[0]) return false; + // remove any existing load/store records for the store being merged into + // the existing record. + purgeRecords(st, DATA_FILE_COUNT); + st->takeExtraSources(0, extra); // save predicate and indirect address if (offRc < offSt) { -- cgit v1.2.3