Mesa (master): nv50/ir: fix ConstantFolding with saturation

[Ilia Mirkin]

Module: Mesa
Branch: master
Commit: 24a799ad35a824fba94062f9b018f603717ed145
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=24a799ad35a824fba94062f9b018f603717ed145

Author: Karol Herbst <karolherbst at gmail.com>
Date:   Sun Jul 30 17:51:22 2017 +0200

nv50/ir: fix ConstantFolding with saturation

For mul(a, +-1) codegen can generate OP_MOV with a saturation flag
set which is ignored at emission. The same can happen with add(a, 0),
and others.

Adding an assert for detecting more of such issues.

Fixes wrongly rendered water in Hitman Absolution running under wine.
Also a few shaders in Mad Max and Alien Isolation produce such MOVs.

CC: <mesa-stable at lists.freedesktop.org>
Signed-off-by: Karol Herbst <karolherbst at gmail.com>
Reviewed-by: Tobias Klausmann <tobias.johannes.klausmann at mni.thm.de>
[imirkin: generalize the fix for other cases]
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>

---

 src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp | 1 +
 src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp  | 8 ++++++++
 2 files changed, 9 insertions(+)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
index 14c00bd187..58594f02c7 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
@@ -2006,6 +2006,7 @@ CodeEmitterNVC0::getSRegEncoding(const ValueRef& ref)
 void
 CodeEmitterNVC0::emitMOV(const Instruction *i)
 {
+   assert(!i->saturate);
    if (i->def(0).getFile() == FILE_PREDICATE) {
       if (i->src(0).getFile() == FILE_GPR) {
          code[0] = 0xfc01c003;
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index dac3e6f814..cfc0dfc53c 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -1509,6 +1509,14 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue &imm0, int s)
    default:
       return;
    }
+
+   // This can get left behind some of the optimizations which simplify
+   // saturatable values.
+   if (newi->op == OP_MOV && newi->saturate) {
+      newi->saturate = 0;
+      newi->op = OP_SAT;
+   }
+
    if (newi->op != op)
       foldCount++;
 }