From cd7db0ab0a871b34d6d07a1db9d3b8b4b8342b35 Mon Sep 17 00:00:00 2001 From: Gert Wollny Date: Thu, 31 May 2018 23:25:09 +0200 Subject: [PATCH] r600/sb: fix rotated register in while loop This patch is based on https://lists.freedesktop.org/archives/mesa-dev/2018-February/185805.html Dave Airlie: "A bunch of CTS tests led me to write tests/shaders/ssa/fs-while-loop-rotate-value.shader_test which r600/sb always fell over on. GCM seems to move some of the copies into other basic blocks, if we don't allow this to happen then it doesn't seem to schedule them badly. Everything I've read on SSA/phi copies say they have to happen in parallel, so keeping them in the same basic block seems like a good way to keep some of that property." This patch differs from the one proposed by Dave in that it only adds the NF_DONT_MOVE flag to copy_move instructions that are created by split_phi* and that are located in loops. Fixes piglit: tests/shaders/ssa/fs-while-loop-rotate-value.shader_test (no regressions in the shader set). It also fixes all failing tests from dEQP-GLES3.functional.shaders.loops.* Signed-off-by: Gert Wollny Reviewed-by: Dave Airlie --- src/gallium/drivers/r600/sb/sb_ra_init.cpp | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/src/gallium/drivers/r600/sb/sb_ra_init.cpp b/src/gallium/drivers/r600/sb/sb_ra_init.cpp index 985e179..c557b86 100644 --- a/src/gallium/drivers/r600/sb/sb_ra_init.cpp +++ b/src/gallium/drivers/r600/sb/sb_ra_init.cpp @@ -545,10 +545,13 @@ void ra_split::split_phi_src(container_node *loc, container_node *c, continue; value *t = sh.create_temp_value(); + alu_node* n = sh.create_copy_mov(t, v); + if (loop) + n->flags |= NF_DONT_MOVE; if (loop && id == 0) - loc->insert_before(sh.create_copy_mov(t, v)); + loc->insert_before(n); else - loc->push_back(sh.create_copy_mov(t, v)); + loc->push_back(n); v = t; sh.coal.add_edge(v, d, coalescer::phi_cost); @@ -566,9 +569,10 @@ void ra_split::split_phi_dst(node* loc, container_node *c, bool loop) { value *t = sh.create_temp_value(); node *cp = sh.create_copy_mov(v, t); - if (loop) + if (loop) { + cp->flags |= NF_DONT_MOVE; static_cast(loc)->push_front(cp); - else + } else loc->insert_after(cp); v = t; } -- 2.7.4