X86: Use a smaller 'mov' instruction for stack probe calls

Prologue emission, in some cases, requires calls to a stack probe helper
function.  The amount of stack to probe is passed as a register
argument in the Win64 ABI but the instruction sequence used is
pessimistic: it assumes that the number of bytes to probe is greater
than 4 GB.

Instead, select a more appropriate opcode depending on the number of
bytes we are going to probe.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230270 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86FrameLowering.cpp b/lib/Target/X86/X86FrameLowering.cpp
index 75fd4fdb434f6727bb3eac51292680e983186417..cf7a4ce4bedabc835d3bce4d3985ca5d9602da31 100644 (file)
--- a/lib/Target/X86/X86FrameLowering.cpp
+++ b/lib/Target/X86/X86FrameLowering.cpp
@@ -820,9 +820,19 @@ void X86FrameLowering::emitPrologue(MachineFunction &MF) const {
     if (Is64Bit) {
       // Handle the 64-bit Windows ABI case where we need to call __chkstk.
       // Function prologue is responsible for adjusting the stack pointer.
-      BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri), X86::RAX)
-        .addImm(NumBytes)
-        .setMIFlag(MachineInstr::FrameSetup);
+      if (isUInt<32>(NumBytes)) {
+        BuildMI(MBB, MBBI, DL, TII.get(X86::MOV32ri), X86::EAX)
+            .addImm(NumBytes)
+            .setMIFlag(MachineInstr::FrameSetup);
+      } else if (isInt<32>(NumBytes)) {
+        BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri32), X86::RAX)
+            .addImm(NumBytes)
+            .setMIFlag(MachineInstr::FrameSetup);
+      } else {
+        BuildMI(MBB, MBBI, DL, TII.get(X86::MOV64ri), X86::RAX)
+            .addImm(NumBytes)
+            .setMIFlag(MachineInstr::FrameSetup);
+      }
     } else {
       // Allocate NumBytes-4 bytes on stack in case of isEAXAlive.
       // We'll also use 4 already allocated bytes for EAX.

diff --git a/test/CodeGen/X86/win64_alloca_dynalloca.ll b/test/CodeGen/X86/win64_alloca_dynalloca.ll
index 810b23593fd0f5c360849faceb6c69c3d7d2c109..abda2272c6625803cf9dc845c7040f270244e14b 100644 (file)
--- a/test/CodeGen/X86/win64_alloca_dynalloca.ll
+++ b/test/CodeGen/X86/win64_alloca_dynalloca.ll
@@ -14,19 +14,19 @@ entry:
   %buf0 = alloca i8, i64 4096, align 1
 
 ; ___chkstk_ms does not adjust %rsp.
-; M64:       $4096, %rax
+; M64:       $4096, %eax
 ; M64: callq ___chkstk_ms
 ; M64: subq  %rax, %rsp
 ; M64: leaq 128(%rsp), %rbp
 
 ; __chkstk does not adjust %rsp.
-; W64:       $4096, %rax
+; W64:       $4096, %eax
 ; W64: callq __chkstk
 ; W64: subq  %rax, %rsp
 ; W64: leaq 128(%rsp), %rbp
 
 ; Use %r11 for the large model.
-; L64:       $4096, %rax
+; L64:       $4096, %eax
 ; L64: movabsq $__chkstk, %r11
 ; L64: callq *%r11
 ; L64: subq  %rax, %rsp

diff --git a/test/CodeGen/X86/win64_eh.ll b/test/CodeGen/X86/win64_eh.ll
index 7b11150d988389c9e964f620fabdff7a573262ac..76d3e86003dd80ed05e998f9b0261df4d7e81e56 100644 (file)
--- a/test/CodeGen/X86/win64_eh.ll
+++ b/test/CodeGen/X86/win64_eh.ll
@@ -35,7 +35,7 @@ entry:
 }
 ; WIN64-LABEL: foo2:
 ; WIN64: .seh_proc foo2
-; WIN64: movabsq $8000, %rax
+; WIN64: movl $8000, %eax
 ; WIN64: callq {{__chkstk|___chkstk_ms}}
 ; WIN64: subq %rax, %rsp
 ; WIN64: .seh_stackalloc 8000