[AMDGPU] Fix op_sel settings for v_cvt_scale32_* and v_cvt_sr_* (llvm#151286)

For OPF_OPSEL_SRCBYTE: Vector instruction uses OPSEL[1:0] to specify a
byte
select for the first source operand. So op_sel [0, 0], [1, 0], [0, 1]
and [1, 1] should map
to byte 0, 1, 2 and 3, respectively.

For OPF_OPSEL_DSTBYTE: OPSEL is used as a destination byte select.
OPSEL[2:3]
specify which byte of the destination to write to. Note that the order
of the bits is different
from that of OPF_OPSEL_SRCBYT. So the mapping should be: op_sel [0, 0],
[0, 1], [1, 0]
and [1, 1] map to byte 0, 1, 2 and 3, respectively.

Fixes: SWDEV-544901

Author: changpeng

llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp

@@ -6675,13 +6675,13 @@ void AMDGPUInstructionSelector::renderSrcAndDstSelToOpSelXForm_0_0(
     MachineInstrBuilder &MIB, const MachineInstr &MI, int OpIdx) const {
   assert(OpIdx >= 0 && "expected to match an immediate operand");
   MIB.addImm(
-      (MI.getOperand(OpIdx).getImm() & 0x2) ? (int64_t)SISrcMods::OP_SEL_0 : 0);
+      (MI.getOperand(OpIdx).getImm() & 0x1) ? (int64_t)SISrcMods::OP_SEL_0 : 0);
 }
 
 void AMDGPUInstructionSelector::renderSrcAndDstSelToOpSelXForm_0_1(
     MachineInstrBuilder &MIB, const MachineInstr &MI, int OpIdx) const {
   assert(OpIdx >= 0 && "expected to match an immediate operand");
-  MIB.addImm((MI.getOperand(OpIdx).getImm() & 0x2)
+  MIB.addImm((MI.getOperand(OpIdx).getImm() & 0x1)
                  ? (int64_t)(SISrcMods::OP_SEL_0 | SISrcMods::DST_OP_SEL)
                  : (int64_t)SISrcMods::DST_OP_SEL);
 }
@@ -6690,13 +6690,13 @@ void AMDGPUInstructionSelector::renderSrcAndDstSelToOpSelXForm_1_0(
     MachineInstrBuilder &MIB, const MachineInstr &MI, int OpIdx) const {
   assert(OpIdx >= 0 && "expected to match an immediate operand");
   MIB.addImm(
-      (MI.getOperand(OpIdx).getImm() & 0x1) ? (int64_t)SISrcMods::OP_SEL_0 : 0);
+      (MI.getOperand(OpIdx).getImm() & 0x2) ? (int64_t)SISrcMods::OP_SEL_0 : 0);
 }
 
 void AMDGPUInstructionSelector::renderSrcAndDstSelToOpSelXForm_1_1(
     MachineInstrBuilder &MIB, const MachineInstr &MI, int OpIdx) const {
   assert(OpIdx >= 0 && "expected to match an immediate operand");
-  MIB.addImm((MI.getOperand(OpIdx).getImm() & 0x1)
+  MIB.addImm((MI.getOperand(OpIdx).getImm() & 0x2)
                  ? (int64_t)(SISrcMods::OP_SEL_0)
                  : 0);
 }
@@ -6719,14 +6719,15 @@ void AMDGPUInstructionSelector::renderSrcAndDstSelToOpSelXForm_2_0(
     MachineInstrBuilder &MIB, const MachineInstr &MI, int OpIdx) const {
   assert(OpIdx >= 0 && "expected to match an immediate operand");
   MIB.addImm(
-      (MI.getOperand(OpIdx).getImm() & 0x1) ? (int64_t)SISrcMods::OP_SEL_0 : 0);
+      (MI.getOperand(OpIdx).getImm() & 0x2) ? (int64_t)SISrcMods::OP_SEL_0 : 0);
 }
 
 void AMDGPUInstructionSelector::renderDstSelToOpSel3XFormXForm(
     MachineInstrBuilder &MIB, const MachineInstr &MI, int OpIdx) const {
   assert(OpIdx >= 0 && "expected to match an immediate operand");
-  MIB.addImm(
-      (MI.getOperand(OpIdx).getImm() & 0x2) ? (int64_t)SISrcMods::DST_OP_SEL  : 0);
+  MIB.addImm((MI.getOperand(OpIdx).getImm() & 0x1)
+                 ? (int64_t)SISrcMods::DST_OP_SEL
+                 : 0);
 }
 
 void AMDGPUInstructionSelector::renderExtractCPol(MachineInstrBuilder &MIB,

llvm/lib/Target/AMDGPU/VOP3Instructions.td

@@ -972,10 +972,10 @@ class SrcAndDstSelToOpSelXForm<int modifier_idx, bit dest_sel> : SDNodeXForm<tim
   unsigned Val = N->getZExtValue();
   unsigned New = 0;
   if (}] # modifier_idx # [{ == 0) {
-    New = (}] # dest_sel # [{ == 1) ? ((Val & 0x2) ? (SISrcMods::OP_SEL_0 | SISrcMods::DST_OP_SEL) : SISrcMods::DST_OP_SEL)
-                                    : ((Val & 0x2) ? SISrcMods::OP_SEL_0 : SISrcMods::NONE);
+    New = (}] # dest_sel # [{ == 1) ? ((Val & 0x1) ? (SISrcMods::OP_SEL_0 | SISrcMods::DST_OP_SEL) : SISrcMods::DST_OP_SEL)
+                                    : ((Val & 0x1) ? SISrcMods::OP_SEL_0 : SISrcMods::NONE);
   } else if (}] # modifier_idx # [{== 1 || }] # modifier_idx # [{ == 2) {
-      New = (Val & 0x1) ? SISrcMods::OP_SEL_0 : SISrcMods::NONE;
+      New = (Val & 0x2) ? SISrcMods::OP_SEL_0 : SISrcMods::NONE;
   }
   return CurDAG->getTargetConstant(New, SDLoc(N), MVT::i32);
 }]>;
@@ -1019,7 +1019,7 @@ def gi_SrcSelToOpSelXForm : GICustomOperandRenderer<"renderSrcSelToOpSelXForm">,
 def DstSelToOpSel3XForm : SDNodeXForm<timm, [{
   uint32_t V = N->getZExtValue();
   return CurDAG->getTargetConstant(
-      (V & 0x2) ? SISrcMods::DST_OP_SEL : SISrcMods::NONE,
+      (V & 0x1) ? SISrcMods::DST_OP_SEL : SISrcMods::NONE,
       SDLoc(N), MVT::i32);
 }]>;
 def gi_DstSelToOpSel3XForm : GICustomOperandRenderer<"renderDstSelToOpSel3XFormXForm">,