aco/gfx10: Emit barrier at the start of NGG VS and TES.

The Navi 1x NGG hardware can hang in certain conditions when
not every wave launched before s_sendmsg(GS_ALLOC_REQ).

As a workaround, to ensure this never happens, let's emit a
workgroup barrier at the beginning of NGG VS and TES.
Note that NGG GS already has a workgroup barrier so it doesn't
need this.

Cc: mesa-stable
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10837>
(cherry picked from commit e6bf5cfe59)
This commit is contained in:
Timur Kristóf 2021-06-19 14:36:15 +02:00 committed by Eric Engestrom
parent f670a5b877
commit 78059b4f52
2 changed files with 8 additions and 1 deletions

View file

@ -2632,7 +2632,7 @@
"description": "aco/gfx10: Emit barrier at the start of NGG VS and TES.",
"nominated": true,
"nomination_type": 0,
"resolution": 0,
"resolution": 1,
"main_sha": null,
"because_sha": null
},

View file

@ -11836,6 +11836,13 @@ void select_program(Program *program,
create_workgroup_barrier(bld);
}
if (program->chip_class == GFX10 &&
program->stage.hw == HWStage::NGG &&
program->stage.num_sw_stages() == 1) {
/* Workaround for Navi 1x HW bug to ensure all NGG waves launch before s_sendmsg(GS_ALLOC_REQ). */
Builder(ctx.program, ctx.block).sopp(aco_opcode::s_barrier, -1u, 0u);
}
if (check_merged_wave_info) {
Temp cond = merged_wave_info_to_mask(&ctx, i);
begin_divergent_if_then(&ctx, &ic_merged_wave_info, cond);