dnz flag only applies for multiplications (e.g. to make 0 * Infinity
becomes 0 instead of NaN). Once we optimize a MAD into an ADD, the dnz
flag no longer makes sense, and upsets the GM107 emitter (since it looks
at the ftz and dnz flags together).
Signed-off-by: Ilia Mirkin <imir...@alum.mit.edu>
---
src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 2 ++
1 file changed, 2 insertions(+)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 04d26dcbf53..307d8762506 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -740,6 +740,7 @@ ConstantFolding::expr(Instruction *i,
// restrictions, so move it into a separate LValue.
bld.setPosition(i, false);
i->op = OP_ADD;
+ i->dnz = 0;
i->setSrc(1, bld.mkMov(bld.getSSA(type), i->getSrc(0), type)->getDef(0));
i->setSrc(0, i->getSrc(2));
i->src(0).mod = i->src(2).mod;
@@ -1131,6 +1132,7 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue
&imm0, int s)
i->setSrc(1, i->getSrc(2));
i->src(1).mod = i->src(2).mod;
i->setSrc(2, NULL);
+ i->dnz = 0;
i->op = OP_ADD;
} else
if (!isFloatType(i->dType) && !i->subOp && !i->src(t).mod &&
!i->src(2).mod) {
--
2.18.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
