[X86] Avoid converting u64 to f32 using x87 on Windows

The code below currently prints less accurate values only on Windows 32-bit. On Windows, the default precision control on x87 is only 53-bit, and FADD triggers rounding with that precision, so the final result may be less accurate. This revision avoids less accurate conversions by using library calls instead.

```

int main() {
    int64_t n = 0b0000000000111111111111111111111111011111111111111111111111111111;
    printf("%lld, %.0f, %.0f", n, (float)n, (float)(uint64_t)n);

    return 0;
}
```

Reviewed By: craig.topper, lebedev.ri

Differential Revision: https://reviews.llvm.org/D141074

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index c88c66d..fb68a9c 100644 (file)
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -21898,6 +21898,13 @@ SDValue X86TargetLowering::LowerUINT_TO_FP(SDValue Op,
   }
 
   assert(SrcVT == MVT::i64 && "Unexpected type in UINT_TO_FP");
+
+  // On Windows, the default precision control on x87 is only 53-bit, and FADD
+  // triggers rounding with that precision, so the final result may be less
+  // accurate. 18014397972611071 is one such case.
+  if (Subtarget.isOSWindows())
+    return SDValue();
+
   SDValue ValueToStore = Src;
   if (isScalarFPTypeInSSEReg(Op.getValueType()) && !Subtarget.is64Bit()) {
     // Bitcasting to f64 here allows us to do a single 64-bit store from

diff --git a/llvm/test/CodeGen/X86/uint64-to-float.ll b/llvm/test/CodeGen/X86/uint64-to-float.ll
index 8b66234..f44986b 100644 (file)
--- a/llvm/test/CodeGen/X86/uint64-to-float.ll
+++ b/llvm/test/CodeGen/X86/uint64-to-float.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=i686-apple-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86
-; RUN: llc < %s -mtriple=x86_64-apple-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86
+; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64
+; RUN: llc < %s -mtriple=i686-windows -mattr=+sse2 | FileCheck %s --check-prefix=X86-WIN
+; RUN: llc < %s -mtriple=x86_64-windows -mattr=+sse2 | FileCheck %s --check-prefix=X64-WIN
 
 ; Verify that we are using the efficient uitofp --> sitofp lowering illustrated
 ; by the compiler_rt implementation of __floatundisf.
@@ -42,6 +44,36 @@ define float @test(i64 %a) nounwind {
 ; X64-NEXT:    cvtsi2ss %rdi, %xmm0
 ; X64-NEXT:    addss %xmm0, %xmm0
 ; X64-NEXT:    retq
+;
+; X86-WIN-LABEL: test:
+; X86-WIN:       # %bb.0: # %entry
+; X86-WIN-NEXT:    pushl %ebp
+; X86-WIN-NEXT:    movl %esp, %ebp
+; X86-WIN-NEXT:    andl $-8, %esp
+; X86-WIN-NEXT:    subl $8, %esp
+; X86-WIN-NEXT:    pushl 12(%ebp)
+; X86-WIN-NEXT:    pushl 8(%ebp)
+; X86-WIN-NEXT:    calll ___floatundisf
+; X86-WIN-NEXT:    addl $8, %esp
+; X86-WIN-NEXT:    movl %ebp, %esp
+; X86-WIN-NEXT:    popl %ebp
+; X86-WIN-NEXT:    retl
+;
+; X64-WIN-LABEL: test:
+; X64-WIN:       # %bb.0: # %entry
+; X64-WIN-NEXT:    testq %rcx, %rcx
+; X64-WIN-NEXT:    js .LBB0_1
+; X64-WIN-NEXT:  # %bb.2: # %entry
+; X64-WIN-NEXT:    cvtsi2ss %rcx, %xmm0
+; X64-WIN-NEXT:    retq
+; X64-WIN-NEXT:  .LBB0_1:
+; X64-WIN-NEXT:    movq %rcx, %rax
+; X64-WIN-NEXT:    shrq %rax
+; X64-WIN-NEXT:    andl $1, %ecx
+; X64-WIN-NEXT:    orq %rax, %rcx
+; X64-WIN-NEXT:    cvtsi2ss %rcx, %xmm0
+; X64-WIN-NEXT:    addss %xmm0, %xmm0
+; X64-WIN-NEXT:    retq
 entry:
   %b = uitofp i64 %a to float
   ret float %b