[llvm] aa79412 - AMDGPU: Fold copy of scalar add of frame index (#115058)

via llvm-commits llvm-commits at lists.llvm.org
Wed Nov 6 09:11:05 PST 2024


Author: Matt Arsenault
Date: 2024-11-06T09:10:58-08:00
New Revision: aa7941289ee5b7d9bdf47e1b0ebf2130a86d9522

URL: https://github.com/llvm/llvm-project/commit/aa7941289ee5b7d9bdf47e1b0ebf2130a86d9522
DIFF: https://github.com/llvm/llvm-project/commit/aa7941289ee5b7d9bdf47e1b0ebf2130a86d9522.diff

LOG: AMDGPU: Fold copy of scalar add of frame index (#115058)

This is a pre-optimization to avoid a regression in a future
commit. Currently we almost always emit frame index with
a v_mov_b32 and use vector adds for the pointer operations. We
need to consider the users of the frame index (or rather, the
transitive users of derived pointer operations) to know whether
the value will be used in a vector or scalar context. This saves
an sgpr->vgpr copy.

This optimization could be more general for any opcode that's
trivially convertible from a scalar to vector form (although this
is a workaround for a proper regbankselect).

Added: 
    llvm/test/CodeGen/AMDGPU/fold-operands-s-add-copy-to-vgpr.mir

Modified: 
    llvm/lib/Target/AMDGPU/SIFoldOperands.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
index 0b8be0d88170c4..096d0316e9dc08 100644
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -78,6 +78,12 @@ class SIFoldOperandsImpl {
   bool frameIndexMayFold(const MachineInstr &UseMI, int OpNo,
                          const MachineOperand &OpToFold) const;
 
+  /// Fold %vgpr = COPY (S_ADD_I32 x, frameindex)
+  ///
+  ///   => %vgpr = V_ADD_U32 x, frameindex
+  bool foldCopyToVGPROfScalarAddOfFrameIndex(Register DstReg, Register SrcReg,
+                                             MachineInstr &MI) const;
+
   bool updateOperand(FoldCandidate &Fold) const;
 
   bool canUseImmWithOpSel(FoldCandidate &Fold) const;
@@ -224,6 +230,67 @@ bool SIFoldOperandsImpl::frameIndexMayFold(
   return OpNo == VIdx && SIdx == -1;
 }
 
+/// Fold %vgpr = COPY (S_ADD_I32 x, frameindex)
+///
+///   => %vgpr = V_ADD_U32 x, frameindex
+bool SIFoldOperandsImpl::foldCopyToVGPROfScalarAddOfFrameIndex(
+    Register DstReg, Register SrcReg, MachineInstr &MI) const {
+  if (TRI->isVGPR(*MRI, DstReg) && TRI->isSGPRReg(*MRI, SrcReg) &&
+      MRI->hasOneNonDBGUse(SrcReg)) {
+    MachineInstr *Def = MRI->getVRegDef(SrcReg);
+    if (Def && Def->getOpcode() == AMDGPU::S_ADD_I32 &&
+        Def->getOperand(3).isDead()) {
+      MachineOperand *Src0 = &Def->getOperand(1);
+      MachineOperand *Src1 = &Def->getOperand(2);
+
+      // TODO: This is profitable with more operand types, and for more
+      // opcodes. But ultimately this is working around poor / nonexistent
+      // regbankselect.
+      if (!Src0->isFI() && !Src1->isFI())
+        return false;
+
+      if (Src0->isFI())
+        std::swap(Src0, Src1);
+
+      MachineBasicBlock *MBB = Def->getParent();
+      const DebugLoc &DL = Def->getDebugLoc();
+      if (ST->hasAddNoCarry()) {
+        bool UseVOP3 = !Src0->isImm() || TII->isInlineConstant(*Src0);
+        MachineInstrBuilder Add =
+            BuildMI(*MBB, *Def, DL,
+                    TII->get(UseVOP3 ? AMDGPU::V_ADD_U32_e64
+                                     : AMDGPU::V_ADD_U32_e32),
+                    DstReg)
+                .add(*Src0)
+                .add(*Src1)
+                .setMIFlags(Def->getFlags());
+        if (UseVOP3)
+          Add.addImm(0);
+
+        Def->eraseFromParent();
+        MI.eraseFromParent();
+        return true;
+      }
+
+      MachineBasicBlock::LivenessQueryResult Liveness =
+          MBB->computeRegisterLiveness(TRI, AMDGPU::VCC, *Def, 16);
+      if (Liveness == MachineBasicBlock::LQR_Dead) {
+        // TODO: If src1 satisfies operand constraints, use vop3 version.
+        BuildMI(*MBB, *Def, DL, TII->get(AMDGPU::V_ADD_CO_U32_e32), DstReg)
+            .add(*Src0)
+            .add(*Src1)
+            .setOperandDead(3) // implicit-def $vcc
+            .setMIFlags(Def->getFlags());
+        Def->eraseFromParent();
+        MI.eraseFromParent();
+        return true;
+      }
+    }
+  }
+
+  return false;
+}
+
 FunctionPass *llvm::createSIFoldOperandsLegacyPass() {
   return new SIFoldOperandsLegacy();
 }
@@ -1470,9 +1537,10 @@ bool SIFoldOperandsImpl::foldInstOperand(MachineInstr &MI,
 
 bool SIFoldOperandsImpl::tryFoldFoldableCopy(
     MachineInstr &MI, MachineOperand *&CurrentKnownM0Val) const {
+  Register DstReg = MI.getOperand(0).getReg();
   // Specially track simple redefs of m0 to the same value in a block, so we
   // can erase the later ones.
-  if (MI.getOperand(0).getReg() == AMDGPU::M0) {
+  if (DstReg == AMDGPU::M0) {
     MachineOperand &NewM0Val = MI.getOperand(1);
     if (CurrentKnownM0Val && CurrentKnownM0Val->isIdenticalTo(NewM0Val)) {
       MI.eraseFromParent();
@@ -1504,13 +1572,17 @@ bool SIFoldOperandsImpl::tryFoldFoldableCopy(
   if (OpToFold.isReg() && !OpToFold.getReg().isVirtual())
     return false;
 
+  if (OpToFold.isReg() &&
+      foldCopyToVGPROfScalarAddOfFrameIndex(DstReg, OpToFold.getReg(), MI))
+    return true;
+
   // Prevent folding operands backwards in the function. For example,
   // the COPY opcode must not be replaced by 1 in this example:
   //
   //    %3 = COPY %vgpr0; VGPR_32:%3
   //    ...
   //    %vgpr0 = V_MOV_B32_e32 1, implicit %exec
-  if (!MI.getOperand(0).getReg().isVirtual())
+  if (!DstReg.isVirtual())
     return false;
 
   bool Changed = foldInstOperand(MI, OpToFold);

diff  --git a/llvm/test/CodeGen/AMDGPU/fold-operands-s-add-copy-to-vgpr.mir b/llvm/test/CodeGen/AMDGPU/fold-operands-s-add-copy-to-vgpr.mir
new file mode 100644
index 00000000000000..683f02b413315e
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/fold-operands-s-add-copy-to-vgpr.mir
@@ -0,0 +1,394 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx803 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX8 %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX9 %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX10 %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX10 %s
+
+---
+name:  copy_undef
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; CHECK-LABEL: name: copy_undef
+    ; CHECK: [[COPY:%[0-9]+]]:vgpr_32 = COPY undef %2:sreg_32
+    ; CHECK-NEXT: SI_RETURN implicit [[COPY]]
+    %0:sreg_32 = S_MOV_B32 %stack.0
+    %2:vgpr_32 = COPY undef %1:sreg_32
+    SI_RETURN implicit %2
+...
+
+---
+name:  fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; GFX8-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr
+    ; GFX8: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = nuw V_ADD_CO_U32_e32 128, %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr
+    ; GFX9: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = nuw V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr
+    ; GFX10: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = nuw V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    %0:sreg_32 = S_MOV_B32 %stack.0
+    %1:sreg_32 = nuw S_ADD_I32 %0, 128, implicit-def dead $scc
+    %2:vgpr_32 = COPY %1
+    SI_RETURN implicit %2
+...
+
+---
+name:  fold_s_add_i32__const_copy_mov_fi_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; GFX8-LABEL: name: fold_s_add_i32__const_copy_mov_fi_to_virt_vgpr
+    ; GFX8: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 128, %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__const_copy_mov_fi_to_virt_vgpr
+    ; GFX9: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__const_copy_mov_fi_to_virt_vgpr
+    ; GFX10: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    %0:sreg_32 = S_MOV_B32 %stack.0
+    %1:sreg_32 = S_ADD_I32 128, %0, implicit-def dead $scc
+    %2:vgpr_32 = COPY %1
+    SI_RETURN implicit %2
+...
+
+---
+name:  fold_s_add_i32__fi_imm_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; GFX8-LABEL: name: fold_s_add_i32__fi_imm_copy_to_virt_vgpr
+    ; GFX8: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = nuw V_ADD_CO_U32_e32 64, %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__fi_imm_copy_to_virt_vgpr
+    ; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = nuw V_ADD_U32_e64 64, %stack.0, 0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__fi_imm_copy_to_virt_vgpr
+    ; GFX10: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = nuw V_ADD_U32_e64 64, %stack.0, 0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    %0:sreg_32 = nuw S_ADD_I32 %stack.0, 64, implicit-def dead $scc
+    %1:vgpr_32 = COPY %0
+    SI_RETURN implicit %1
+...
+
+---
+name:  fold_s_add_i32__imm_fi_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; GFX8-LABEL: name: fold_s_add_i32__imm_fi_copy_to_virt_vgpr
+    ; GFX8: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = nuw V_ADD_CO_U32_e32 64, %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__imm_fi_copy_to_virt_vgpr
+    ; GFX9: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = nuw V_ADD_U32_e64 64, %stack.0, 0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__imm_fi_copy_to_virt_vgpr
+    ; GFX10: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = nuw V_ADD_U32_e64 64, %stack.0, 0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    %0:sreg_32 = nuw S_ADD_I32 64, %stack.0, implicit-def dead $scc
+    %1:vgpr_32 = COPY %0
+    SI_RETURN implicit %1
+...
+
+---
+name:  fold_s_add_i32__mov_fi_const_copy_to_phys_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; GFX8-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_phys_vgpr
+    ; GFX8: $vgpr0 = V_ADD_CO_U32_e32 128, %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit $vgpr0
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_phys_vgpr
+    ; GFX9: $vgpr0 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit $vgpr0
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_phys_vgpr
+    ; GFX10: $vgpr0 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit $vgpr0
+    %0:sreg_32 = S_MOV_B32 %stack.0
+    %1:sreg_32 = S_ADD_I32 %0, 128, implicit-def dead $scc
+    $vgpr0 = COPY %1
+    SI_RETURN implicit $vgpr0
+...
+
+---
+name:  fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr_live_vcc
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    liveins: $vcc
+    ; GFX8-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr_live_vcc
+    ; GFX8: liveins: $vcc
+    ; GFX8-NEXT: {{  $}}
+    ; GFX8-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, 128, implicit-def dead $scc
+    ; GFX8-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[S_ADD_I32_]]
+    ; GFX8-NEXT: SI_RETURN implicit [[COPY]], implicit $vcc
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr_live_vcc
+    ; GFX9: liveins: $vcc
+    ; GFX9-NEXT: {{  $}}
+    ; GFX9-NEXT: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]], implicit $vcc
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr_live_vcc
+    ; GFX10: liveins: $vcc
+    ; GFX10-NEXT: {{  $}}
+    ; GFX10-NEXT: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]], implicit $vcc
+    %0:sreg_32 = S_MOV_B32 %stack.0
+    %1:sreg_32 = S_ADD_I32 %0, 128, implicit-def dead $scc
+    %2:vgpr_32 = COPY %1
+    SI_RETURN implicit %2, implicit $vcc
+...
+
+---
+name:  fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr_live_scc
+tracksRegLiveness: true
+frameInfo:
+  maxAlignment:    4
+  localFrameSize:  16384
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; CHECK-LABEL: name: fold_s_add_i32__mov_fi_const_copy_to_virt_vgpr_live_scc
+    ; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, 128, implicit-def $scc
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[S_ADD_I32_]]
+    ; CHECK-NEXT: SI_RETURN implicit [[COPY]], implicit $scc
+    %0:sreg_32 = S_MOV_B32 %stack.0
+    %1:sreg_32 = S_ADD_I32 %0, 128, implicit-def $scc
+    %2:vgpr_32 = COPY %1
+    SI_RETURN implicit %2, implicit $scc
+...
+
+---
+name:  fold_s_add_i32__mov_fi_reg_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    liveins: $sgpr8
+
+    ; GFX8-LABEL: name: fold_s_add_i32__mov_fi_reg_copy_to_virt_vgpr
+    ; GFX8: liveins: $sgpr8
+    ; GFX8-NEXT: {{  $}}
+    ; GFX8-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX8-NEXT: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 [[COPY]], %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__mov_fi_reg_copy_to_virt_vgpr
+    ; GFX9: liveins: $sgpr8
+    ; GFX9-NEXT: {{  $}}
+    ; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX9-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__mov_fi_reg_copy_to_virt_vgpr
+    ; GFX10: liveins: $sgpr8
+    ; GFX10-NEXT: {{  $}}
+    ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX10-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    %0:sreg_32 = COPY $sgpr8
+    %1:sreg_32 = S_MOV_B32 %stack.0
+    %2:sreg_32 = S_ADD_I32 %0, %1, implicit-def dead $scc
+    %3:vgpr_32 = COPY %2
+    SI_RETURN implicit %3
+...
+
+
+---
+name:  fold_s_add_i32__reg_copy_mov_fi_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    liveins: $sgpr8
+
+    ; GFX8-LABEL: name: fold_s_add_i32__reg_copy_mov_fi_to_virt_vgpr
+    ; GFX8: liveins: $sgpr8
+    ; GFX8-NEXT: {{  $}}
+    ; GFX8-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX8-NEXT: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 [[COPY]], %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__reg_copy_mov_fi_to_virt_vgpr
+    ; GFX9: liveins: $sgpr8
+    ; GFX9-NEXT: {{  $}}
+    ; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX9-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__reg_copy_mov_fi_to_virt_vgpr
+    ; GFX10: liveins: $sgpr8
+    ; GFX10-NEXT: {{  $}}
+    ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX10-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    %0:sreg_32 = COPY $sgpr8
+    %1:sreg_32 = S_MOV_B32 %stack.0
+    %2:sreg_32 = S_ADD_I32 %1, %0, implicit-def dead $scc
+    %3:vgpr_32 = COPY %2
+    SI_RETURN implicit %3
+...
+
+---
+name:  fold_s_add_i32__fi_fi_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+  - { id: 1, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; CHECK-LABEL: name: fold_s_add_i32__fi_fi_copy_to_virt_vgpr
+    ; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, %stack.1, implicit-def dead $scc
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[COPY]]
+    ; CHECK-NEXT: SI_RETURN implicit [[COPY]]
+    %0:sreg_32 = S_ADD_I32 %stack.0, %stack.1, implicit-def dead $scc
+    %1:vgpr_32 = COPY %1
+    SI_RETURN implicit %1
+...
+
+---
+name:  fold_s_add_i32__fi_const_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; GFX8-LABEL: name: fold_s_add_i32__fi_const_copy_to_virt_vgpr
+    ; GFX8: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 128, %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__fi_const_copy_to_virt_vgpr
+    ; GFX9: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__fi_const_copy_to_virt_vgpr
+    ; GFX10: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    %0:sreg_32 = S_ADD_I32 %stack.0, 128, implicit-def dead $scc
+    %1:vgpr_32 = COPY %0
+    SI_RETURN implicit %1
+...
+
+---
+name:  fold_s_add_i32__const_fi_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; GFX8-LABEL: name: fold_s_add_i32__const_fi_copy_to_virt_vgpr
+    ; GFX8: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 128, %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__const_fi_copy_to_virt_vgpr
+    ; GFX9: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__const_fi_copy_to_virt_vgpr
+    ; GFX10: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e32_]]
+    %0:sreg_32 = S_ADD_I32 128, %stack.0, implicit-def dead $scc
+    %1:vgpr_32 = COPY %0
+    SI_RETURN implicit %1
+...
+
+---
+name:  fold_s_add_i32__fi_reg_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    liveins: $sgpr8
+    ; GFX8-LABEL: name: fold_s_add_i32__fi_reg_copy_to_virt_vgpr
+    ; GFX8: liveins: $sgpr8
+    ; GFX8-NEXT: {{  $}}
+    ; GFX8-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX8-NEXT: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 [[COPY]], %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__fi_reg_copy_to_virt_vgpr
+    ; GFX9: liveins: $sgpr8
+    ; GFX9-NEXT: {{  $}}
+    ; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX9-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__fi_reg_copy_to_virt_vgpr
+    ; GFX10: liveins: $sgpr8
+    ; GFX10-NEXT: {{  $}}
+    ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX10-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    %0:sreg_32 = COPY $sgpr8
+    %1:sreg_32 = S_ADD_I32 %stack.0, %0, implicit-def dead $scc
+    %2:vgpr_32 = COPY %1
+    SI_RETURN implicit %2
+...
+
+---
+name:  fold_s_add_i32__reg_fi_copy_to_virt_vgpr
+tracksRegLiveness: true
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    liveins: $sgpr8
+    ; GFX8-LABEL: name: fold_s_add_i32__reg_fi_copy_to_virt_vgpr
+    ; GFX8: liveins: $sgpr8
+    ; GFX8-NEXT: {{  $}}
+    ; GFX8-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX8-NEXT: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 [[COPY]], %stack.0, implicit-def dead $vcc, implicit $exec
+    ; GFX8-NEXT: SI_RETURN implicit [[V_ADD_CO_U32_e32_]]
+    ;
+    ; GFX9-LABEL: name: fold_s_add_i32__reg_fi_copy_to_virt_vgpr
+    ; GFX9: liveins: $sgpr8
+    ; GFX9-NEXT: {{  $}}
+    ; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX9-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX9-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    ;
+    ; GFX10-LABEL: name: fold_s_add_i32__reg_fi_copy_to_virt_vgpr
+    ; GFX10: liveins: $sgpr8
+    ; GFX10-NEXT: {{  $}}
+    ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
+    ; GFX10-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY]], %stack.0, 0, implicit $exec
+    ; GFX10-NEXT: SI_RETURN implicit [[V_ADD_U32_e64_]]
+    %0:sreg_32 = COPY $sgpr8
+    %1:sreg_32 = S_ADD_I32 %0, %stack.0, implicit-def dead $scc
+    %2:vgpr_32 = COPY %1
+    SI_RETURN implicit %2
+...


        


More information about the llvm-commits mailing list