nv50/ir: restore OP_SELP to be a regular instruction

Actually OP_SELP doesn't need to be a compare instruction. Instead we
just need to set the NOT modifier when building the instruction.
While we are at it, fix the dst register type and use a GPR.

Suggested by Ilia Mirkin.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
index 8268e08..a78b3f9 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
@@ -112,7 +112,7 @@ private:
 
    void emitSET(const CmpInstruction *);
    void emitSLCT(const CmpInstruction *);
-   void emitSELP(const CmpInstruction *);
+   void emitSELP(const Instruction *);
 
    void emitTEXBAR(const Instruction *);
    void emitTEX(const TexInstruction *);
@@ -1045,11 +1045,11 @@ CodeEmitterGK110::emitSLCT(const CmpInstruction *i)
    }
 }
 
-void CodeEmitterGK110::emitSELP(const CmpInstruction *i)
+void CodeEmitterGK110::emitSELP(const Instruction *i)
 {
    emitForm_21(i, 0x250, 0x050);
 
-   if ((i->setCond == CC_NOT_P) ^ (bool)(i->src(2).mod & Modifier(NV50_IR_MOD_NOT)))
+   if (i->src(2).mod & Modifier(NV50_IR_MOD_NOT))
       code[1] |= 1 << 13;
 }
 
@@ -1937,7 +1937,7 @@ CodeEmitterGK110::emitInstruction(Instruction *insn)
       emitSET(insn->asCmp());
       break;
    case OP_SELP:
-      emitSELP(insn->asCmp());
+      emitSELP(insn);
       break;
    case OP_SLCT:
       emitSLCT(insn->asCmp());

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 d588d7e..65fcd64 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
@@ -120,7 +120,7 @@ private:
 
    void emitSET(const CmpInstruction *);
    void emitSLCT(const CmpInstruction *);
-   void emitSELP(const CmpInstruction *);
+   void emitSELP(const Instruction *);
 
    void emitTEXBAR(const Instruction *);
    void emitTEX(const TexInstruction *);
@@ -1175,11 +1175,11 @@ CodeEmitterNVC0::emitSLCT(const CmpInstruction *i)
       code[0] |= 1 << 5;
 }
 
-void CodeEmitterNVC0::emitSELP(const CmpInstruction *i)
+void CodeEmitterNVC0::emitSELP(const Instruction *i)
 {
    emitForm_A(i, HEX64(20000000, 00000004));
 
-   if (i->setCond == CC_NOT_P || i->src(2).mod & Modifier(NV50_IR_MOD_NOT))
+   if (i->src(2).mod & Modifier(NV50_IR_MOD_NOT))
       code[1] |= 1 << 20;
 }
 
@@ -2438,7 +2438,7 @@ CodeEmitterNVC0::emitInstruction(Instruction *insn)
       emitSET(insn->asCmp());
       break;
    case OP_SELP:
-      emitSELP(insn->asCmp());
+      emitSELP(insn);
       break;
    case OP_SLCT:
       emitSLCT(insn->asCmp());

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_inlines.h b/src/gallium/drivers/nouveau/codegen/nv50_ir_inlines.h
index 02e6157..e465f24 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_inlines.h
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_inlines.h
@@ -281,14 +281,14 @@ Value *TexInstruction::getIndirectS() const
 
 CmpInstruction *Instruction::asCmp()
 {
-   if (op >= OP_SET_AND && op <= OP_SLCT)
+   if (op >= OP_SET_AND && op <= OP_SLCT && op != OP_SELP)
       return static_cast<CmpInstruction *>(this);
    return NULL;
 }
 
 const CmpInstruction *Instruction::asCmp() const
 {
-   if (op >= OP_SET_AND && op <= OP_SLCT)
+   if (op >= OP_SET_AND && op <= OP_SLCT && op != OP_SELP)
       return static_cast<const CmpInstruction *>(this);
    return NULL;
 }

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 21a6f1e..d181f15 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
@@ -1067,10 +1067,10 @@ NVC0LoweringPass::handleSharedATOM(Instruction *atom)
                    TYPE_U32, ld->getDef(0), atom->getSrc(1));
       set->setPredicate(CC_P, ld->getDef(1));
 
-      CmpInstruction *selp =
-         bld.mkCmp(OP_SELP, CC_NOT_P, TYPE_U32, bld.getSSA(4, FILE_ADDRESS),
-                   TYPE_U32, ld->getDef(0), atom->getSrc(2),
-                   set->getDef(0));
+      Instruction *selp =
+         bld.mkOp3(OP_SELP, TYPE_U32, bld.getSSA(), ld->getDef(0),
+                   atom->getSrc(2), set->getDef(0));
+      selp->src(2).mod = Modifier(NV50_IR_MOD_NOT);
       selp->setPredicate(CC_P, ld->getDef(1));
 
       stVal = selp->getDef(0);