[llvm] bc4b2c7 - [X86][APX] Add NF instructions to convertToThreeAddress functions (#130969)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Mar 12 22:23:54 PDT 2025
Author: Phoebe Wang
Date: 2025-03-13T13:23:50+08:00
New Revision: bc4b2c74fe4eae40652e0f79ee9e0397110c0423
URL: https://github.com/llvm/llvm-project/commit/bc4b2c74fe4eae40652e0f79ee9e0397110c0423
DIFF: https://github.com/llvm/llvm-project/commit/bc4b2c74fe4eae40652e0f79ee9e0397110c0423.diff
LOG: [X86][APX] Add NF instructions to convertToThreeAddress functions (#130969)
Since #130488, we have NF instructions when converting to three address
instructions.
Added:
llvm/test/CodeGen/X86/apx/nf-regressions.ll
Modified:
llvm/lib/Target/X86/X86InstrInfo.cpp
Removed:
################################################################################
diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp
index 24002cbbcab57..99a0259119d42 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.cpp
+++ b/llvm/lib/Target/X86/X86InstrInfo.cpp
@@ -1283,11 +1283,14 @@ MachineInstr *X86InstrInfo::convertToThreeAddressWithLEA(unsigned MIOpc,
MachineInstrBuilder MIB =
BuildMI(MBB, MBBI, MI.getDebugLoc(), get(Opcode), OutRegLEA);
+#define CASE_NF(OP) \
+ case X86::OP: \
+ case X86::OP##_NF:
switch (MIOpc) {
default:
llvm_unreachable("Unreachable!");
- case X86::SHL8ri:
- case X86::SHL16ri: {
+ CASE_NF(SHL8ri)
+ CASE_NF(SHL16ri) {
unsigned ShAmt = MI.getOperand(2).getImm();
MIB.addReg(0)
.addImm(1LL << ShAmt)
@@ -1296,23 +1299,23 @@ MachineInstr *X86InstrInfo::convertToThreeAddressWithLEA(unsigned MIOpc,
.addReg(0);
break;
}
- case X86::INC8r:
- case X86::INC16r:
+ CASE_NF(INC8r)
+ CASE_NF(INC16r)
addRegOffset(MIB, InRegLEA, true, 1);
break;
- case X86::DEC8r:
- case X86::DEC16r:
+ CASE_NF(DEC8r)
+ CASE_NF(DEC16r)
addRegOffset(MIB, InRegLEA, true, -1);
break;
- case X86::ADD8ri:
+ CASE_NF(ADD8ri)
+ CASE_NF(ADD16ri)
case X86::ADD8ri_DB:
- case X86::ADD16ri:
case X86::ADD16ri_DB:
addRegOffset(MIB, InRegLEA, true, MI.getOperand(2).getImm());
break;
- case X86::ADD8rr:
+ CASE_NF(ADD8rr)
+ CASE_NF(ADD16rr)
case X86::ADD8rr_DB:
- case X86::ADD16rr:
case X86::ADD16rr_DB: {
Src2 = MI.getOperand(2).getReg();
Src2SubReg = MI.getOperand(2).getSubReg();
@@ -1449,7 +1452,7 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
switch (MIOpc) {
default:
llvm_unreachable("Unreachable!");
- case X86::SHL64ri: {
+ CASE_NF(SHL64ri) {
assert(MI.getNumOperands() >= 3 && "Unknown shift instruction!");
unsigned ShAmt = getTruncatedShiftCount(MI, 2);
if (!isTruncatedShiftCountForLEA(ShAmt))
@@ -1469,7 +1472,7 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
.addReg(0);
break;
}
- case X86::SHL32ri: {
+ CASE_NF(SHL32ri) {
assert(MI.getNumOperands() >= 3 && "Unknown shift instruction!");
unsigned ShAmt = getTruncatedShiftCount(MI, 2);
if (!isTruncatedShiftCountForLEA(ShAmt))
@@ -1501,20 +1504,20 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
LV->getVarInfo(SrcReg).Kills.push_back(NewMI);
break;
}
- case X86::SHL8ri:
+ CASE_NF(SHL8ri)
Is8BitOp = true;
[[fallthrough]];
- case X86::SHL16ri: {
+ CASE_NF(SHL16ri) {
assert(MI.getNumOperands() >= 3 && "Unknown shift instruction!");
unsigned ShAmt = getTruncatedShiftCount(MI, 2);
if (!isTruncatedShiftCountForLEA(ShAmt))
return nullptr;
return convertToThreeAddressWithLEA(MIOpc, MI, LV, LIS, Is8BitOp);
}
- case X86::INC64r:
- case X86::INC32r: {
+ CASE_NF(INC64r)
+ CASE_NF(INC32r) {
assert(MI.getNumOperands() >= 2 && "Unknown inc instruction!");
- unsigned Opc = MIOpc == X86::INC64r
+ unsigned Opc = (MIOpc == X86::INC64r || MIOpc == X86::INC64r_NF)
? X86::LEA64r
: (Is64Bit ? X86::LEA64_32r : X86::LEA32r);
bool isKill;
@@ -1536,10 +1539,10 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
LV->getVarInfo(SrcReg).Kills.push_back(NewMI);
break;
}
- case X86::DEC64r:
- case X86::DEC32r: {
+ CASE_NF(DEC64r)
+ CASE_NF(DEC32r) {
assert(MI.getNumOperands() >= 2 && "Unknown dec instruction!");
- unsigned Opc = MIOpc == X86::DEC64r
+ unsigned Opc = (MIOpc == X86::DEC64r || MIOpc == X86::DEC64r_NF)
? X86::LEA64r
: (Is64Bit ? X86::LEA64_32r : X86::LEA32r);
@@ -1562,20 +1565,21 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
LV->getVarInfo(SrcReg).Kills.push_back(NewMI);
break;
}
- case X86::DEC8r:
- case X86::INC8r:
+ CASE_NF(DEC8r)
+ CASE_NF(INC8r)
Is8BitOp = true;
[[fallthrough]];
- case X86::DEC16r:
- case X86::INC16r:
+ CASE_NF(DEC16r)
+ CASE_NF(INC16r)
return convertToThreeAddressWithLEA(MIOpc, MI, LV, LIS, Is8BitOp);
- case X86::ADD64rr:
+ CASE_NF(ADD64rr)
+ CASE_NF(ADD32rr)
case X86::ADD64rr_DB:
- case X86::ADD32rr:
case X86::ADD32rr_DB: {
assert(MI.getNumOperands() >= 3 && "Unknown add instruction!");
unsigned Opc;
- if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_DB)
+ if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_NF ||
+ MIOpc == X86::ADD64rr_DB)
Opc = X86::LEA64r;
else
Opc = Is64Bit ? X86::LEA64_32r : X86::LEA32r;
@@ -1620,21 +1624,21 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
NumRegOperands = 3;
break;
}
- case X86::ADD8rr:
+ CASE_NF(ADD8rr)
case X86::ADD8rr_DB:
Is8BitOp = true;
[[fallthrough]];
- case X86::ADD16rr:
+ CASE_NF(ADD16rr)
case X86::ADD16rr_DB:
return convertToThreeAddressWithLEA(MIOpc, MI, LV, LIS, Is8BitOp);
- case X86::ADD64ri32:
+ CASE_NF(ADD64ri32)
case X86::ADD64ri32_DB:
assert(MI.getNumOperands() >= 3 && "Unknown add instruction!");
NewMI = addOffset(
BuildMI(MF, MI.getDebugLoc(), get(X86::LEA64r)).add(Dest).add(Src),
MI.getOperand(2));
break;
- case X86::ADD32ri:
+ CASE_NF(ADD32ri)
case X86::ADD32ri_DB: {
assert(MI.getNumOperands() >= 3 && "Unknown add instruction!");
unsigned Opc = Is64Bit ? X86::LEA64_32r : X86::LEA32r;
@@ -1659,18 +1663,18 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
LV->getVarInfo(SrcReg).Kills.push_back(NewMI);
break;
}
- case X86::ADD8ri:
+ CASE_NF(ADD8ri)
case X86::ADD8ri_DB:
Is8BitOp = true;
[[fallthrough]];
- case X86::ADD16ri:
+ CASE_NF(ADD16ri)
case X86::ADD16ri_DB:
return convertToThreeAddressWithLEA(MIOpc, MI, LV, LIS, Is8BitOp);
- case X86::SUB8ri:
- case X86::SUB16ri:
+ CASE_NF(SUB8ri)
+ CASE_NF(SUB16ri)
/// FIXME: Support these similar to ADD8ri/ADD16ri*.
return nullptr;
- case X86::SUB32ri: {
+ CASE_NF(SUB32ri) {
if (!MI.getOperand(2).isImm())
return nullptr;
int64_t Imm = MI.getOperand(2).getImm();
@@ -1701,7 +1705,7 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
break;
}
- case X86::SUB64ri32: {
+ CASE_NF(SUB64ri32) {
if (!MI.getOperand(2).isImm())
return nullptr;
int64_t Imm = MI.getOperand(2).getImm();
@@ -2034,6 +2038,7 @@ MachineInstr *X86InstrInfo::convertToThreeAddress(MachineInstr &MI,
break;
}
}
+#undef CASE_NF
if (!NewMI)
return nullptr;
diff --git a/llvm/test/CodeGen/X86/apx/nf-regressions.ll b/llvm/test/CodeGen/X86/apx/nf-regressions.ll
new file mode 100644
index 0000000000000..40503d85a1ddb
--- /dev/null
+++ b/llvm/test/CodeGen/X86/apx/nf-regressions.ll
@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=x86_64 -mattr=+nf -verify-machineinstrs | FileCheck %s
+
+define void @convertToThreeAddress(ptr %arg, ptr %arg1) {
+; CHECK-LABEL: convertToThreeAddress:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: movslq (%rdi), %rax
+; CHECK-NEXT: movslq (%rsi), %rcx
+; CHECK-NEXT: subq %rax, %rcx
+; CHECK-NEXT: leaq 1(%rcx), %rax
+; CHECK-NEXT: js .LBB0_1
+; CHECK-NEXT: .p2align 4
+; CHECK-NEXT: .LBB0_6: # %bb
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: cmpq $1, %rax
+; CHECK-NEXT: jg .LBB0_6
+; CHECK-NEXT: .LBB0_5: # %bb16
+; CHECK-NEXT: retq
+; CHECK-NEXT: .LBB0_1:
+; CHECK-NEXT: xorl %edx, %edx
+; CHECK-NEXT: .p2align 4
+; CHECK-NEXT: .LBB0_2: # %bb10
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: testb %dl, %dl
+; CHECK-NEXT: je .LBB0_3
+; CHECK-NEXT: # %bb.7: # %bb11
+; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
+; CHECK-NEXT: testq %rcx, %rcx
+; CHECK-NEXT: jns .LBB0_2
+; CHECK-NEXT: jmp .LBB0_5
+; CHECK-NEXT: .LBB0_3: # %bb10
+; CHECK-NEXT: xorl %ecx, %ecx
+; CHECK-NEXT: testb %cl, %cl
+; CHECK-NEXT: jne .LBB0_5
+; CHECK-NEXT: .p2align 4
+; CHECK-NEXT: .LBB0_4: # %bb12
+; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: cmpq $1, %rax
+; CHECK-NEXT: jg .LBB0_4
+; CHECK-NEXT: jmp .LBB0_5
+entry:
+ %i = load i32, ptr %arg, align 4
+ %i2 = sext i32 %i to i64
+ %i3 = load i32, ptr %arg1, align 4
+ %i4 = sext i32 %i3 to i64
+ %i5 = sub nsw i64 %i4, %i2
+ %i6 = add nsw i64 %i5, 1
+ %i7 = icmp sgt i64 %i5, -1
+ br i1 %i7, label %bb, label %bb10
+
+bb: ; preds = %bb, %entry
+ %i8 = phi i64 [ %i6, %entry ], [ poison, %bb ]
+ %i9 = icmp sgt i64 %i8, 1
+ br i1 %i9, label %bb, label %bb16
+
+bb10: ; preds = %bb11, %entry
+ switch i32 poison, label %bb16 [
+ i32 1, label %bb11
+ i32 2, label %bb12
+ ]
+
+bb11: ; preds = %bb10
+ br i1 %i7, label %bb10, label %bb16
+
+bb12: ; preds = %bb14, %bb10
+ %i13 = phi i64 [ poison, %bb14 ], [ %i6, %bb10 ]
+ br label %bb14
+
+bb14: ; preds = %bb12
+ %i15 = icmp sgt i64 %i13, 1
+ br i1 %i15, label %bb12, label %bb16
+
+bb16: ; preds = %bb14, %bb11, %bb10, %bb
+ ret void
+}
More information about the llvm-commits
mailing list