summaryrefslogtreecommitdiffstats
path: root/src
diff options
context:
space:
mode:
authorIlia Mirkin <imirkin@alum.mit.edu>2015-05-23 01:57:41 -0400
committerIlia Mirkin <imirkin@alum.mit.edu>2015-05-23 22:15:15 -0400
commitfa7f9f123b70f313d3c073b52c9c16b4b8df28f8 (patch)
tree9bfa8d3abe58af174cc13a0818026ae6ab8139f6 /src
parentf972b223c4cb4ec58a9451cbac5d120ac9deb336 (diff)
downloadexternal_mesa3d-fa7f9f123b70f313d3c073b52c9c16b4b8df28f8.zip
external_mesa3d-fa7f9f123b70f313d3c073b52c9c16b4b8df28f8.tar.gz
external_mesa3d-fa7f9f123b70f313d3c073b52c9c16b4b8df28f8.tar.bz2
nv50/ir: avoid messing up arg1 of PFETCH
There can be scenarios where the "indirect" arg of a PFETCH becomes known, and so the code will attempt to propagate it. Use this opportunity to just fold it into the first argument, and prevent the load propagation pass from touching PFETCH further. This fixes gs-input-array-vec4-index-rd.shader_test and vs-output-array-vec4-index-wr-before-gs.shader_test on nvc0 at least. Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu> Reviewed-by: Tobias Klausmann <tobias.johannes.klausmann@mni.thm.de> Cc: "10.5 10.6" <mesa-stable@lists.freedesktop.org>
Diffstat (limited to 'src')
-rw-r--r--src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp20
1 files changed, 18 insertions, 2 deletions
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 72dd31e..b7fcd56 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -236,6 +236,9 @@ LoadPropagation::visit(BasicBlock *bb)
if (i->op == OP_CALL) // calls have args as sources, they must be in regs
continue;
+ if (i->op == OP_PFETCH) // pfetch expects arg1 to be a reg
+ continue;
+
if (i->srcExists(1))
checkSwapSrc01(i);
@@ -581,6 +584,11 @@ ConstantFolding::expr(Instruction *i,
case OP_POPCNT:
res.data.u32 = util_bitcount(a->data.u32 & b->data.u32);
break;
+ case OP_PFETCH:
+ // The two arguments to pfetch are logically added together. Normally
+ // the second argument will not be constant, but that can happen.
+ res.data.u32 = a->data.u32 + b->data.u32;
+ break;
default:
return;
}
@@ -595,7 +603,9 @@ ConstantFolding::expr(Instruction *i,
i->getSrc(0)->reg.data = res.data;
- if (i->op == OP_MAD || i->op == OP_FMA) {
+ switch (i->op) {
+ case OP_MAD:
+ case OP_FMA: {
i->op = OP_ADD;
i->setSrc(1, i->getSrc(0));
@@ -610,8 +620,14 @@ ConstantFolding::expr(Instruction *i,
bld.setPosition(i, false);
i->setSrc(1, bld.loadImm(NULL, res.data.u32));
}
- } else {
+ break;
+ }
+ case OP_PFETCH:
+ // Leave PFETCH alone... we just folded its 2 args into 1.
+ break;
+ default:
i->op = i->saturate ? OP_SAT : OP_MOV; /* SAT handled by unary() */
+ break;
}
i->subOp = 0;
}