nvc0/ir: handle zero and negative sqrt arguments

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
index 8ac3b26..18e8e67 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
@@ -1567,10 +1567,22 @@ NVC0LoweringPass::handleMOD(Instruction *i)
 bool
 NVC0LoweringPass::handleSQRT(Instruction *i)
 {
-   Instruction *rsq = bld.mkOp1(OP_RSQ, i->dType,
-                                bld.getSSA(typeSizeof(i->dType)), i->getSrc(0));
+   Value *pred = bld.getSSA(1, FILE_PREDICATE);
+   Value *zero = bld.getSSA();
+   Instruction *rsq;
+
+   bld.mkOp1(OP_MOV, TYPE_U32, zero, bld.mkImm(0));
+   if (i->dType == TYPE_F64)
+      zero = bld.mkOp2v(OP_MERGE, TYPE_U64, bld.getSSA(8), zero, zero);
+   bld.mkCmp(OP_SET, CC_LE, i->dType, pred, i->dType, i->getSrc(0), zero);
+   bld.mkOp1(OP_MOV, i->dType, i->getDef(0), zero)->setPredicate(CC_P, pred);
+   rsq = bld.mkOp1(OP_RSQ, i->dType,
+                   bld.getSSA(typeSizeof(i->dType)), i->getSrc(0));
+   rsq->setPredicate(CC_NOT_P, pred);
    i->op = OP_MUL;
    i->setSrc(1, rsq->getDef(0));
+   i->setPredicate(CC_NOT_P, pred);
+
 
    return true;
 }