diff options
| author | Rhys Perry <pendingchaos02@gmail.com> | 2022-07-21 19:23:38 +0100 |
|---|---|---|
| committer | Dylan Baker <dylan.c.baker@intel.com> | 2022-08-11 10:30:38 -0700 |
| commit | 71703783c22690ad0e14cd3eeb79619706bc04a6 (patch) | |
| tree | c96ca02bdd5ed8c2dab955f36a9a6334e11a0868 | |
| parent | e63f5e6eb41749f09ae923e3d59c56ea719d80d7 (diff) | |
| download | mesa-71703783c22690ad0e14cd3eeb79619706bc04a6.tar.gz | |
aco: fix LdsBranchVmemWARHazard with 2+ branch chains
For example, "DS -> branch -> VMEM -> branch -> DS".
fossil-db (navi10):
Totals from 639 (0.40% of 161220) affected shaders:
Instrs: 629090 -> 628254 (-0.13%); split: -0.19%, +0.06%
CodeSize: 3410164 -> 3406748 (-0.10%); split: -0.14%, +0.04%
Latency: 7834755 -> 7821011 (-0.18%); split: -0.70%, +0.52%
InvThroughput: 1369698 -> 1374495 (+0.35%); split: -0.12%, +0.47%
A lot of the fossil-db changes are noise.
threekingdoms.8db138826c386a62.1.foz/0b222ed175eebad0 is an example of a
shader that actually has this issue.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Fixes: c037ba1bb7a ("aco/gfx10: Mitigate LdsBranchVmemWARHazard.")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17697>
(cherry picked from commit b17e59a03b2c31460145b691dc5b39b13e340003)
| -rw-r--r-- | .pick_status.json | 2 | ||||
| -rw-r--r-- | src/amd/compiler/aco_insert_NOPs.cpp | 3 |
2 files changed, 4 insertions, 1 deletions
diff --git a/.pick_status.json b/.pick_status.json index 5d6a4c130a7..a7b5fe33c77 100644 --- a/.pick_status.json +++ b/.pick_status.json @@ -895,7 +895,7 @@ "description": "aco: fix LdsBranchVmemWARHazard with 2+ branch chains", "nominated": true, "nomination_type": 1, - "resolution": 0, + "resolution": 1, "main_sha": null, "because_sha": "c037ba1bb7aba99bd15e063bbdbc6d4c68cf2384" }, diff --git a/src/amd/compiler/aco_insert_NOPs.cpp b/src/amd/compiler/aco_insert_NOPs.cpp index 5dd1c7183e8..69aab519788 100644 --- a/src/amd/compiler/aco_insert_NOPs.cpp +++ b/src/amd/compiler/aco_insert_NOPs.cpp @@ -787,6 +787,9 @@ handle_instruction_gfx10(State& state, NOP_ctx_gfx10& ctx, aco_ptr<Instruction>& wait->definitions[0] = Definition(sgpr_null, s1); wait->imm = 0; new_instructions.emplace_back(std::move(wait)); + + ctx.has_VMEM = instr->isVMEM() || instr->isGlobal() || instr->isScratch(); + ctx.has_DS = instr->isDS(); } /* NSAToVMEMBug |