[SystemZ] Improve foldMemoryOperandImpl().

Fold MS(G)RKC -> MS(G)C. Review: Ulrich Weigand Differential Revision: https://reviews.llvm.org/D76771
2025-01-16 05:01:56 +00:00 · 2020-03-17 13:19:30 +01:00 · 2020-03-17 13:19:30 +01:00 · f481d48893
commit f481d48893
parent b3f13bc165
4 changed files with 226 additions and 6 deletions
--- a/llvm/lib/Target/SystemZ/SystemZInstrFormats.td
+++ b/llvm/lib/Target/SystemZ/SystemZInstrFormats.td
@ -4773,7 +4773,9 @@ multiclass BinaryRIAndKPseudo<string key, SDPatternOperator operator,
 class MemFoldPseudo<string mnemonic, RegisterOperand cls, bits<5> bytes,
                    AddressingMode mode>
  : Pseudo<(outs cls:$R1), (ins cls:$R2, mode:$XBD2), []> {
-    let OpKey = mnemonic#"rk"#cls;
+    let OpKey = !subst("mscrk", "msrkc",
+                !subst("msgcrk", "msgrkc",
+                mnemonic#"rk"#cls));
    let OpType = "mem";
    let MemKey = mnemonic#cls;
    let MemType = "pseudo";
--- a/llvm/lib/Target/SystemZ/SystemZInstrInfo.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZInstrInfo.cpp
@ -1198,18 +1198,17 @@ MachineInstr *SystemZInstrInfo::foldMemoryOperandImpl(
  // See if this is a 3-address instruction that is convertible to 2-address
  // and suitable for folding below.  Only try this with virtual registers
  // and a provided VRM (during regalloc).
-  if (SystemZ::getTwoOperandOpcode(Opcode) != -1) {
+  if (NumOps == 3 && SystemZ::getTargetMemOpcode(MemOpcode) != -1) {
    if (VRM == nullptr)
      return nullptr;
    else {
-      assert(NumOps == 3 && "Expected two source registers.");
      Register DstReg = MI.getOperand(0).getReg();
      Register DstPhys =
          (Register::isVirtualRegister(DstReg) ? VRM->getPhys(DstReg) : DstReg);
      Register SrcReg = (OpNum == 2 ? MI.getOperand(1).getReg()
                                    : ((OpNum == 1 && MI.isCommutable())
                                           ? MI.getOperand(2).getReg()
-                                         : Register()));
+                                           : Register()));
      if (DstPhys && !SystemZ::GRH32BitRegClass.contains(DstPhys) && SrcReg &&
          Register::isVirtualRegister(SrcReg) &&
          DstPhys == VRM->getPhys(SrcReg))
--- a/llvm/lib/Target/SystemZ/SystemZInstrInfo.td
+++ b/llvm/lib/Target/SystemZ/SystemZInstrInfo.td
@ -1348,8 +1348,8 @@ def  MSG  : BinaryRXY<"msg",  0xE30C, mul, GR64, load, 8>;

 // Multiplication of memory, setting the condition code.
 let Predicates = [FeatureMiscellaneousExtensions2], Defs = [CC] in {
-  def MSC  : BinaryRXY<"msc",  0xE353, null_frag, GR32, load, 4>;
-  def MSGC : BinaryRXY<"msgc", 0xE383, null_frag, GR64, load, 8>;
+  defm MSC  : BinaryRXYAndPseudo<"msc",  0xE353, null_frag, GR32, load, 4>;
+  defm MSGC : BinaryRXYAndPseudo<"msgc", 0xE383, null_frag, GR64, load, 8>;
 }

 // Multiplication of a register, producing two results.
--- a/llvm/test/CodeGen/SystemZ/foldmemop-msc.mir
+++ b/llvm/test/CodeGen/SystemZ/foldmemop-msc.mir
@ -0,0 +1,219 @@
+# RUN: llc -mtriple=s390x-linux-gnu -mcpu=z14 -start-before=greedy %s -o - \
+# RUN:   | FileCheck %s
+#
+# Test folding of a memory operand into logical compare with an immediate.
+
+--- |
+  define i32 @fun0(i32* %src, i32 %arg) { ret i32 0 }
+  define i64 @fun1(i64* %src, i64 %arg) { ret i64 0 }
+  define i32 @fun2(i32* %src, i32 %arg) { ret i32 0 }
+  define i64 @fun3(i64* %src, i64 %arg) { ret i64 0 }
+...
+
+
+# CHECK-LABEL: fun0:
+# CHECK-LABEL: .LBB0_2:
+# CHECK:	msc     %r0, 164(%r15)                  # 4-byte Folded Reload
+---
+name:            fun0
+alignment:       16
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: grx32bit }
+  - { id: 1, class: grx32bit }
+  - { id: 2, class: addr64bit }
+  - { id: 3, class: gr32bit }
+  - { id: 4, class: grx32bit }
+  - { id: 5, class: grx32bit }
+  - { id: 6, class: gr32bit }
+  - { id: 7, class: gr32bit }
+  - { id: 8, class: gr32bit }
+liveins:
+  - { reg: '$r2d', virtual-reg: '%2' }
+  - { reg: '$r3l', virtual-reg: '%3' }
+frameInfo:
+  maxAlignment:    1
+  hasOpaqueSPAdjustment: true
+machineFunctionInfo: {}
+body:             |
+  bb.0:
+    successors: %bb.1(0x30000000), %bb.2(0x50000000)
+    liveins: $r2d, $r3l
+  
+    %3:gr32bit = COPY $r3l
+    %2:addr64bit = COPY $r2d
+    %6:gr32bit = LHIMux 0
+    CHIMux %3, 0, implicit-def $cc
+    %8:gr32bit = LHIMux 0
+    BRC 14, 6, %bb.2, implicit killed $cc
+    J %bb.1
+  
+  bb.1:
+    %8:gr32bit = LMux %2, 0, $noreg :: (load 4 from %ir.src)
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+  
+  bb.2:
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+    %6:gr32bit = MSRKC %8, %6, implicit-def $cc
+    %6:gr32bit = LOCHIMux %6, 1, 14, 6, implicit killed $cc
+    %7:gr32bit = NRK %3, %6, implicit-def dead $cc
+    $r2l = COPY %7
+    Return implicit $r2l
+
+...
+
+
+# CHECK-LABEL: fun1:
+# CHECK-LABEL: .LBB1_2:
+# CHECK:	msc     %r0, 164(%r15)                  # 4-byte Folded Reload
+---
+name:            fun1
+alignment:       16
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: grx32bit }
+  - { id: 1, class: grx32bit }
+  - { id: 2, class: addr64bit }
+  - { id: 3, class: gr32bit }
+  - { id: 4, class: grx32bit }
+  - { id: 5, class: grx32bit }
+  - { id: 6, class: gr32bit }
+  - { id: 7, class: gr32bit }
+  - { id: 8, class: gr32bit }
+liveins:
+  - { reg: '$r2d', virtual-reg: '%2' }
+  - { reg: '$r3l', virtual-reg: '%3' }
+frameInfo:
+  maxAlignment:    1
+  hasOpaqueSPAdjustment: true
+machineFunctionInfo: {}
+body:             |
+  bb.0:
+    successors: %bb.1(0x30000000), %bb.2(0x50000000)
+    liveins: $r2d, $r3l
+  
+    %3:gr32bit = COPY $r3l
+    %2:addr64bit = COPY $r2d
+    %6:gr32bit = LHIMux 0
+    CHIMux %3, 0, implicit-def $cc
+    %8:gr32bit = LHIMux 0
+    BRC 14, 6, %bb.2, implicit killed $cc
+    J %bb.1
+  
+  bb.1:
+    %8:gr32bit = LMux %2, 0, $noreg :: (load 4 from %ir.src)
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+  
+  bb.2:
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+    %6:gr32bit = MSRKC %6, %8, implicit-def $cc
+    %6:gr32bit = LOCHIMux %6, 1, 14, 6, implicit killed $cc
+    %7:gr32bit = NRK %3, %6, implicit-def dead $cc
+    $r2l = COPY %7
+    Return implicit $r2l
+
+...
+
+
+# CHECK-LABEL: fun2:
+# CHECK-LABEL: .LBB2_2:
+# CHECK:	msgc    %r0, 168(%r15)                  # 8-byte Folded Reload
+---
+name:            fun2
+alignment:       16
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: gr64bit }
+  - { id: 1, class: gr64bit }
+  - { id: 2, class: addr64bit }
+  - { id: 3, class: gr64bit }
+  - { id: 4, class: gr64bit }
+  - { id: 5, class: gr64bit }
+  - { id: 6, class: gr64bit }
+  - { id: 7, class: gr64bit }
+  - { id: 8, class: gr64bit }
+liveins:
+  - { reg: '$r2d', virtual-reg: '%2' }
+  - { reg: '$r3d', virtual-reg: '%3' }
+frameInfo:
+  maxAlignment:    1
+  hasOpaqueSPAdjustment: true
+machineFunctionInfo: {}
+body:             |
+  bb.0:
+    successors: %bb.1(0x30000000), %bb.2(0x50000000)
+    liveins: $r2d, $r3d
+  
+    %3:gr64bit = COPY $r3d
+    %2:addr64bit = COPY $r2d
+    %6:gr64bit = LGHI 0
+    CGHI %3, 0, implicit-def $cc
+    %8:gr64bit = LGHI 0
+    BRC 14, 6, %bb.2, implicit killed $cc
+    J %bb.1
+  
+  bb.1:
+    %8:gr64bit = LG %2, 0, $noreg :: (load 8 from %ir.src)
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+  
+  bb.2:
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+    %6:gr64bit = MSGRKC %8, %6, implicit-def $cc
+    %6:gr64bit = LOCGHI %6, 1, 14, 6, implicit killed $cc
+    %7:gr64bit = NGRK %3, %6, implicit-def dead $cc
+    $r2d = COPY %7
+    Return implicit $r2d
+
+...
+
+
+# CHECK-LABEL: fun3:
+# CHECK-LABEL: .LBB3_2:
+# CHECK:	msgc    %r0, 168(%r15)                  # 8-byte Folded Reload
+---
+name:            fun3
+alignment:       16
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: gr64bit }
+  - { id: 1, class: gr64bit }
+  - { id: 2, class: addr64bit }
+  - { id: 3, class: gr64bit }
+  - { id: 4, class: gr64bit }
+  - { id: 5, class: gr64bit }
+  - { id: 6, class: gr64bit }
+  - { id: 7, class: gr64bit }
+  - { id: 8, class: gr64bit }
+liveins:
+  - { reg: '$r2d', virtual-reg: '%2' }
+  - { reg: '$r3d', virtual-reg: '%3' }
+frameInfo:
+  maxAlignment:    1
+  hasOpaqueSPAdjustment: true
+machineFunctionInfo: {}
+body:             |
+  bb.0:
+    successors: %bb.1(0x30000000), %bb.2(0x50000000)
+    liveins: $r2d, $r3d
+  
+    %3:gr64bit = COPY $r3d
+    %2:addr64bit = COPY $r2d
+    %6:gr64bit = LGHI 0
+    CGHI %3, 0, implicit-def $cc
+    %8:gr64bit = LGHI 0
+    BRC 14, 6, %bb.2, implicit killed $cc
+    J %bb.1
+  
+  bb.1:
+    %8:gr64bit = LG %2, 0, $noreg :: (load 8 from %ir.src)
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+  
+  bb.2:
+    INLINEASM &"", 1, 12, implicit-def dead early-clobber $r0d, 12, implicit-def dead early-clobber $r1d, 12, implicit-def dead early-clobber $r2d, 12, implicit-def dead early-clobber $r3d, 12, implicit-def dead early-clobber $r4d, 12, implicit-def dead early-clobber $r5d, 12, implicit-def dead early-clobber $r6d, 12, implicit-def dead early-clobber $r7d, 12, implicit-def dead early-clobber $r8d, 12, implicit-def dead early-clobber $r9d, 12, implicit-def dead early-clobber $r10d, 12, implicit-def dead early-clobber $r11d, 12, implicit-def dead early-clobber $r12d, 12, implicit-def dead early-clobber $r13d, 12, implicit-def dead early-clobber $r14d, 12, implicit-def early-clobber $r15d
+    %6:gr64bit = MSGRKC %6, %8, implicit-def $cc
+    %6:gr64bit = LOCGHI %6, 1, 14, 6, implicit killed $cc
+    %7:gr64bit = NGRK %3, %6, implicit-def dead $cc
+    $r2d = COPY %7
+    Return implicit $r2d
+
+...