[llvm] 2cdb886 - [X86] Convert `mov moffs64` to `movabs` automatically (#172954)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Dec 19 05:27:59 PST 2025
Author: R
Date: 2025-12-19T13:27:54Z
New Revision: 2cdb88698d16a8cbf34642773541664c8fb9aad3
URL: https://github.com/llvm/llvm-project/commit/2cdb88698d16a8cbf34642773541664c8fb9aad3
DIFF: https://github.com/llvm/llvm-project/commit/2cdb88698d16a8cbf34642773541664c8fb9aad3.diff
LOG: [X86] Convert `mov moffs64` to `movabs` automatically (#172954)
Opcodes 0xA0-0xA3 can access a 64-bit absolute address. Before this
change, LLVM would require this to be written as `movabs`, and writing
it as `mov` would silently truncate the address.
After this change, if `mov moffset` is used with a constant expression
which evaluates to a value that doesn't fit in 32 bits, the instruction
will automatically be changed to `movabs`. This should match the
behavior of more recent versions of gas.
The one existing test which expected a silent truncation + sign-extend
is removed.
This change does not affect `mov` opcodes that reference an external
symbol. Using `mov` will continue to generate a 32-bit address and
reloc_signed_4byte, and `movabs` is required to specify a 64-bit
address.
Fixes #73481
Added:
llvm/test/MC/X86/intel-syntax-movabs-large.s
llvm/test/MC/X86/movabs-large.s
Modified:
llvm/lib/Target/X86/AsmParser/X86Operand.h
llvm/lib/Target/X86/X86InstrAsmAlias.td
llvm/lib/Target/X86/X86InstrOperands.td
llvm/test/MC/X86/x86-64.s
Removed:
################################################################################
diff --git a/llvm/lib/Target/X86/AsmParser/X86Operand.h b/llvm/lib/Target/X86/AsmParser/X86Operand.h
index a92272573bacd..a31a7c3b4bd0e 100644
--- a/llvm/lib/Target/X86/AsmParser/X86Operand.h
+++ b/llvm/lib/Target/X86/AsmParser/X86Operand.h
@@ -506,6 +506,18 @@ struct X86Operand final : public MCParsedAsmOperand {
return isMemOffs() && Mem.ModeSize == 64 && (!Mem.Size || Mem.Size == 64);
}
+ // Returns true only for a moffset that requires *more than* 32 bits.
+ bool isMemConstOffs64() const {
+ if (!isMemOffs() || Mem.ModeSize != 64)
+ return false;
+
+ const MCConstantExpr *CE = dyn_cast<MCConstantExpr>(getMemDisp());
+ if (!CE)
+ return false;
+
+ return !isInt<32>(CE->getValue());
+ }
+
bool isPrefix() const { return Kind == Prefix; }
bool isReg() const override { return Kind == Register; }
bool isDXReg() const { return Kind == DXRegister; }
diff --git a/llvm/lib/Target/X86/X86InstrAsmAlias.td b/llvm/lib/Target/X86/X86InstrAsmAlias.td
index 5a4c3f61672b3..1d56512e7a5cd 100644
--- a/llvm/lib/Target/X86/X86InstrAsmAlias.td
+++ b/llvm/lib/Target/X86/X86InstrAsmAlias.td
@@ -667,6 +667,15 @@ def : InstAlias<"jmpl\t$seg, $off", (FARJMP32i i32imm:$off, i16imm:$seg)>, Req
// Match 'movq <largeimm>, <reg>' as an alias for movabsq.
def : InstAlias<"mov{q}\t{$imm, $reg|$reg, $imm}", (MOV64ri GR64:$reg, i64imm:$imm), 0>;
+// Match 'movX <largeimm>, <reg a>' and its reverse as an alias for movabsX.
+def : InstAlias<"mov{b}\t{$src, %al|al, $src}", (MOV8ao64 offset64const:$src), 0>;
+def : InstAlias<"mov{w}\t{$src, %ax|ax, $src}", (MOV16ao64 offset64const:$src), 0>;
+def : InstAlias<"mov{l}\t{$src, %eax|eax, $src}", (MOV32ao64 offset64const:$src), 0>;
+def : InstAlias<"mov{q}\t{$src, %rax|rax, $src}", (MOV64ao64 offset64const:$src), 0>;
+def : InstAlias<"mov{b}\t{%al, $dst|$dst, al}", (MOV8o64a offset64const:$dst), 0>;
+def : InstAlias<"mov{w}\t{%ax, $dst|$dst, ax}", (MOV16o64a offset64const:$dst), 0>;
+def : InstAlias<"mov{l}\t{%eax, $dst|$dst, eax}", (MOV32o64a offset64const:$dst), 0>;
+def : InstAlias<"mov{q}\t{%rax, $dst|$dst, rax}", (MOV64o64a offset64const:$dst), 0>;
// Match 'movd GR64, MMX' as an alias for movq to be compatible with gas,
// which supports this due to an old AMD documentation bug when 64-bit mode was
diff --git a/llvm/lib/Target/X86/X86InstrOperands.td b/llvm/lib/Target/X86/X86InstrOperands.td
index 6ba07f74d74c5..69ce4f8552609 100644
--- a/llvm/lib/Target/X86/X86InstrOperands.td
+++ b/llvm/lib/Target/X86/X86InstrOperands.td
@@ -280,6 +280,10 @@ let RenderMethod = "addMemOffsOperands" in {
let Name = "MemOffs64_64";
let SuperClasses = [X86Mem64AsmOperand];
}
+ def X86MemConstOffs64_AsmOperand : AsmOperandClass {
+ let Name = "MemConstOffs64";
+ let SuperClasses = [X86Mem8AsmOperand];
+ }
} // RenderMethod = "addMemOffsOperands"
class X86SrcIdxOperand<string printMethod, AsmOperandClass parserMatchClass>
@@ -330,6 +334,9 @@ def offset64_32 : X86MemOffsOperand<i64imm, "printMemOffs32",
def offset64_64 : X86MemOffsOperand<i64imm, "printMemOffs64",
X86MemOffs64_64AsmOperand>;
+def offset64const : X86MemOffsOperand<i64imm, "printMemOffset",
+ X86MemConstOffs64_AsmOperand>;
+
def ccode : Operand<i8> {
let PrintMethod = "printCondCode";
let OperandNamespace = "X86";
diff --git a/llvm/test/MC/X86/intel-syntax-movabs-large.s b/llvm/test/MC/X86/intel-syntax-movabs-large.s
new file mode 100644
index 0000000000000..eb4353dbaab17
--- /dev/null
+++ b/llvm/test/MC/X86/intel-syntax-movabs-large.s
@@ -0,0 +1,69 @@
+// RUN: llvm-mc -triple x86_64- -x86-asm-syntax=intel --show-encoding %s | FileCheck %s
+
+// These should map mov -> movabs
+
+// CHECK: movabsb %al, 78187493520
+// CHECK: encoding: [0xa2,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov [0x1234567890], al
+// CHECK: movabsw %ax, 78187493520
+// CHECK: encoding: [0x66,0xa3,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov [0x1234567890], ax
+// CHECK: movabsl %eax, 78187493520
+// CHECK: encoding: [0xa3,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov [0x1234567890], eax
+// CHECK: movabsq %rax, 78187493520
+// CHECK: encoding: [0x48,0xa3,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov [0x1234567890], rax
+
+// CHECK: movabsb 78187493520, %al
+// CHECK: encoding: [0xa0,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov al, [0x1234567890]
+// CHECK: movabsw 78187493520, %ax
+// CHECK: encoding: [0x66,0xa1,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov ax, [0x1234567890]
+// CHECK: movabsl 78187493520, %eax
+// CHECK: encoding: [0xa1,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov eax, [0x1234567890]
+// CHECK: movabsq 78187493520, %rax
+// CHECK: encoding: [0x48,0xa1,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ mov rax, [0x1234567890]
+
+// These should *NOT* map mov -> movabs
+
+// CHECK: movb %al, 305419896
+// CHECK: encoding: [0x88,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov [0x12345678], al
+// CHECK: movw %ax, 305419896
+// CHECK: encoding: [0x66,0x89,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov [0x12345678], ax
+// CHECK: movl %eax, 305419896
+// CHECK: encoding: [0x89,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov [0x12345678], eax
+// CHECK: movq %rax, 305419896
+// CHECK: encoding: [0x48,0x89,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov [0x12345678], rax
+
+// CHECK: movb 305419896, %al
+// CHECK: encoding: [0x8a,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov al, [0x12345678]
+// CHECK: movw 305419896, %ax
+// CHECK: encoding: [0x66,0x8b,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov ax, [0x12345678]
+// CHECK: movl 305419896, %eax
+// CHECK: encoding: [0x8b,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov eax, [0x12345678]
+// CHECK: movq 305419896, %rax
+// CHECK: encoding: [0x48,0x8b,0x04,0x25,0x78,0x56,0x34,0x12]
+ mov rax, [0x12345678]
+
+// Test sign extension
+
+// CHECK: movb %al, 2147483647
+// CHECK: encoding: [0x88,0x04,0x25,0xff,0xff,0xff,0x7f]
+ mov [0x7fffffff], al
+// CHECK: movabsb %al, 2147483648
+// CHECK: encoding: [0xa2,0x00,0x00,0x00,0x80,0x00,0x00,0x00,0x00]
+ mov [0x80000000], al
+// CHECK: movb %al, -2147483648
+// CHECK: encoding: [0x88,0x04,0x25,0x00,0x00,0x00,0x80]
+ mov [0xffffffff80000000], al
diff --git a/llvm/test/MC/X86/movabs-large.s b/llvm/test/MC/X86/movabs-large.s
new file mode 100644
index 0000000000000..731e66c3516ac
--- /dev/null
+++ b/llvm/test/MC/X86/movabs-large.s
@@ -0,0 +1,69 @@
+// RUN: llvm-mc -triple x86_64- --show-encoding %s | FileCheck %s
+
+// These should map mov -> movabs
+
+// CHECK: movabsb %al, 78187493520
+// CHECK: encoding: [0xa2,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movb %al, 0x1234567890
+// CHECK: movabsw %ax, 78187493520
+// CHECK: encoding: [0x66,0xa3,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movw %ax, 0x1234567890
+// CHECK: movabsl %eax, 78187493520
+// CHECK: encoding: [0xa3,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movl %eax, 0x1234567890
+// CHECK: movabsq %rax, 78187493520
+// CHECK: encoding: [0x48,0xa3,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movq %rax, 0x1234567890
+
+// CHECK: movabsb 78187493520, %al
+// CHECK: encoding: [0xa0,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movb 0x1234567890, %al
+// CHECK: movabsw 78187493520, %ax
+// CHECK: encoding: [0x66,0xa1,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movw 0x1234567890, %ax
+// CHECK: movabsl 78187493520, %eax
+// CHECK: encoding: [0xa1,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movl 0x1234567890, %eax
+// CHECK: movabsq 78187493520, %rax
+// CHECK: encoding: [0x48,0xa1,0x90,0x78,0x56,0x34,0x12,0x00,0x00,0x00]
+ movq 0x1234567890, %rax
+
+// These should *NOT* map mov -> movabs
+
+// CHECK: movb %al, 305419896
+// CHECK: encoding: [0x88,0x04,0x25,0x78,0x56,0x34,0x12]
+ movb %al, 0x12345678
+// CHECK: movw %ax, 305419896
+// CHECK: encoding: [0x66,0x89,0x04,0x25,0x78,0x56,0x34,0x12]
+ movw %ax, 0x12345678
+// CHECK: movl %eax, 305419896
+// CHECK: encoding: [0x89,0x04,0x25,0x78,0x56,0x34,0x12]
+ movl %eax, 0x12345678
+// CHECK: movq %rax, 305419896
+// CHECK: encoding: [0x48,0x89,0x04,0x25,0x78,0x56,0x34,0x12]
+ movq %rax, 0x12345678
+
+// CHECK: movb 305419896, %al
+// CHECK: encoding: [0x8a,0x04,0x25,0x78,0x56,0x34,0x12]
+ movb 0x12345678, %al
+// CHECK: movw 305419896, %ax
+// CHECK: encoding: [0x66,0x8b,0x04,0x25,0x78,0x56,0x34,0x12]
+ movw 0x12345678, %ax
+// CHECK: movl 305419896, %eax
+// CHECK: encoding: [0x8b,0x04,0x25,0x78,0x56,0x34,0x12]
+ movl 0x12345678, %eax
+// CHECK: movq 305419896, %rax
+// CHECK: encoding: [0x48,0x8b,0x04,0x25,0x78,0x56,0x34,0x12]
+ movq 0x12345678, %rax
+
+// Test sign extension
+
+// CHECK: movb %al, 2147483647
+// CHECK: encoding: [0x88,0x04,0x25,0xff,0xff,0xff,0x7f]
+ movb %al, 0x7fffffff
+// CHECK: movabsb %al, 2147483648
+// CHECK: encoding: [0xa2,0x00,0x00,0x00,0x80,0x00,0x00,0x00,0x00]
+ movb %al, 0x80000000
+// CHECK: movb %al, -2147483648
+// CHECK: encoding: [0x88,0x04,0x25,0x00,0x00,0x00,0x80]
+ movb %al, 0xffffffff80000000
diff --git a/llvm/test/MC/X86/x86-64.s b/llvm/test/MC/X86/x86-64.s
index 911f4674bd2cc..2da72d52d997c 100644
--- a/llvm/test/MC/X86/x86-64.s
+++ b/llvm/test/MC/X86/x86-64.s
@@ -675,10 +675,6 @@ movl 0, %eax // CHECK: movl 0, %eax # encoding: [0x8b,0x04,0x25,0x00,0x00,0x00
// CHECK: encoding: [0x48,0xc7,0xc0,0x0a,0x00,0x00,0x00]
movq $10, %rax
-// CHECK: movq 81985529216486895, %rax
-// CHECK: encoding: [0x48,0x8b,0x04,0x25,0xef,0xcd,0xab,0x89]
- movq 0x123456789abcdef, %rax
-
// CHECK: movabsb -6066930261531658096, %al
// CHECK: encoding: [0xa0,0x90,0x78,0x56,0x34,0x12,0xef,0xcd,0xab]
movabsb 0xabcdef1234567890,%al
More information about the llvm-commits
mailing list