[AArch64][GlobalISel] Assign FPR banks to loads which are used by integer->float conversions.

G_[US]ITOFP users of loads on AArch64 can operate on both gpr and fpr banks for scalars.
Because of this, if their source is a load, then that load can be assigned to an fpr
bank and therefore avoid having to do a cross bank copy via a gpr->fpr conversion.

Differential Revision: https://reviews.llvm.org/D94701

Author: aemerson

llvm/lib/Target/AArch64/GISel/AArch64RegisterBankInfo.cpp

@@ -680,11 +680,18 @@ AArch64RegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
     break;
   }
   case TargetOpcode::G_SITOFP:
-  case TargetOpcode::G_UITOFP:
+  case TargetOpcode::G_UITOFP: {
     if (MRI.getType(MI.getOperand(0).getReg()).isVector())
       break;
-    OpRegBankIdx = {PMI_FirstFPR, PMI_FirstGPR};
+    // Integer to FP conversions don't necessarily happen between GPR -> FPR
+    // regbanks. They can also be done within an FPR register.
+    Register SrcReg = MI.getOperand(1).getReg();
+    if (getRegBank(SrcReg, MRI, TRI) == &AArch64::FPRRegBank)
+      OpRegBankIdx = {PMI_FirstFPR, PMI_FirstFPR};
+    else
+      OpRegBankIdx = {PMI_FirstFPR, PMI_FirstGPR};
     break;
+  }
   case TargetOpcode::G_FPTOSI:
   case TargetOpcode::G_FPTOUI:
     if (MRI.getType(MI.getOperand(0).getReg()).isVector())
@@ -722,7 +729,8 @@ AArch64RegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
         // assume this was a floating point load in the IR.
         // If it was not, we would have had a bitcast before
         // reaching that instruction.
-        if (onlyUsesFP(UseMI, MRI, TRI)) {
+        // Int->FP conversion operations are also captured in onlyDefinesFP().
+        if (onlyUsesFP(UseMI, MRI, TRI) || onlyDefinesFP(UseMI, MRI, TRI)) {
           OpRegBankIdx[0] = PMI_FirstFPR;
           break;
         }

llvm/test/CodeGen/AArch64/GlobalISel/regbank-fp-use-def.mir

@@ -4,7 +4,7 @@
 # Check that we correctly assign register banks based off of instructions which
 # only use or only define FPRs.
 #
-# For example, G_SITOFP takes in a GPR, but only ever produces values on FPRs.
+# For example, G_SITOFP may take in a GPR, but only ever produces values on FPRs.
 # Some instructions can have inputs/outputs on either FPRs or GPRs. If one of
 # those instructions takes in the result of a G_SITOFP as a source, we should
 # put that source on a FPR.
@@ -361,3 +361,47 @@ body:             |
     %phi:_(s32) = G_PHI %gpr_copy(s32), %bb.0, %unmerge_1(s32), %bb.1
     $s0 = COPY %phi(s32)
     RET_ReallyLR implicit $s0
+
+...
+---
+name:            load_used_by_sitofp
+legalized:       true
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $x0
+    ; The load should be assigned an fpr bank because it's used by the sitofp.
+    ; The sitofp should assign both src and dest to FPR, resulting in no copies.
+    ; CHECK-LABEL: name: load_used_by_sitofp
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr(p0) = COPY $x0
+    ; CHECK: [[LOAD:%[0-9]+]]:fpr(s32) = G_LOAD [[COPY]](p0) :: (load 4)
+    ; CHECK: [[SITOFP:%[0-9]+]]:fpr(s32) = G_SITOFP [[LOAD]](s32)
+    ; CHECK: $s0 = COPY [[SITOFP]](s32)
+    ; CHECK: RET_ReallyLR implicit $s0
+    %0:_(p0) = COPY $x0
+    %1:_(s32) = G_LOAD %0 :: (load 4)
+    %2:_(s32) = G_SITOFP %1:_(s32)
+    $s0 = COPY %2(s32)
+    RET_ReallyLR implicit $s0
+...
+---
+name:            load_used_by_uitofp
+legalized:       true
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: $x0
+    ; CHECK-LABEL: name: load_used_by_uitofp
+    ; CHECK: liveins: $x0
+    ; CHECK: [[COPY:%[0-9]+]]:gpr(p0) = COPY $x0
+    ; CHECK: [[LOAD:%[0-9]+]]:fpr(s32) = G_LOAD [[COPY]](p0) :: (load 4)
+    ; CHECK: [[UITOFP:%[0-9]+]]:fpr(s32) = G_UITOFP [[LOAD]](s32)
+    ; CHECK: $s0 = COPY [[UITOFP]](s32)
+    ; CHECK: RET_ReallyLR implicit $s0
+    %0:_(p0) = COPY $x0
+    %1:_(s32) = G_LOAD %0 :: (load 4)
+    %2:_(s32) = G_UITOFP %1:_(s32)
+    $s0 = COPY %2(s32)
+    RET_ReallyLR implicit $s0
+...