X86: Constant fold converting vector setcc results to float.

Since the result of a SETCC for X86 is 0 or -1 in each lane, we can
move unary operations, in this case [su]int_to_fp through the mask
operation and constant fold the operation away. Generally speaking:
  UNARYOP(AND(VECTOR_CMP(x,y), constant))
      --> AND(VECTOR_CMP(x,y), constant2)
where constant2 is UNARYOP(constant).

This implements the transform where UNARYOP is [su]int_to_fp.

For example, consider the simple function:
define <4 x float> @foo(<4 x float> %val, <4 x float> %test) nounwind {
  %cmp = fcmp oeq <4 x float> %val, %test
  %ext = zext <4 x i1> %cmp to <4 x i32>
  %result = sitofp <4 x i32> %ext to <4 x float>
  ret <4 x float> %result
}

Before this change, the SSE code is generated as:
LCPI0_0:
  .long 1                       ## 0x1
  .long 1                       ## 0x1
  .long 1                       ## 0x1
  .long 1                       ## 0x1
  .section  __TEXT,__text,regular,pure_instructions
  .globl  _foo
  .align  4, 0x90
_foo:                                   ## @foo
  cmpeqps %xmm1, %xmm0
  andps LCPI0_0(%rip), %xmm0
  cvtdq2ps  %xmm0, %xmm0
  retq

After, the code is improved to:
LCPI0_0:
  .long 1065353216              ## float 1.000000e+00
  .long 1065353216              ## float 1.000000e+00
  .long 1065353216              ## float 1.000000e+00
  .long 1065353216              ## float 1.000000e+00
  .section  __TEXT,__text,regular,pure_instructions
  .globl  _foo
  .align  4, 0x90
_foo:                                   ## @foo
  cmpeqps %xmm1, %xmm0
  andps LCPI0_0(%rip), %xmm0
  retq

The cvtdq2ps has been constant folded away and the floating point 1.0f
vector lanes are materialized directly via the ModRM operand of andps.

llvm-svn: 213342

1 files changed, 18 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/x86-setcc-int-to-fp-combine.ll b/llvm/test/CodeGen/X86/x86-setcc-int-to-fp-combine.ll
new file mode 100644
index 00000000000..d691685f1dd
--- /dev/null
+++ b/llvm/test/CodeGen/X86/x86-setcc-int-to-fp-combine.ll
@@ -0,0 +1,18 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s
+
+define <4 x float> @foo(<4 x float> %val, <4 x float> %test) nounwind {
+; CHECK-LABEL: LCPI0_0
+; CHECK-NEXT: .long 1065353216              ## float 1.000000e+00
+; CHECK-NEXT: .long 1065353216              ## float 1.000000e+00
+; CHECK-NEXT: .long 1065353216              ## float 1.000000e+00
+; CHECK-NEXT: .long 1065353216              ## float 1.000000e+00
+; CHECK-LABEL: foo:
+; CHECK: cmpeqps %xmm1, %xmm0
+; CHECK-NEXT: andps LCPI0_0(%rip), %xmm0
+; CHECK-NEXT: retq
+
+  %cmp = fcmp oeq <4 x float> %val, %test
+  %ext = zext <4 x i1> %cmp to <4 x i32>
+  %result = sitofp <4 x i32> %ext to <4 x float>
+  ret <4 x float> %result
+}