Optimize some vfp comparisons to integer ones. This patch implements the simplest case when the following conditions are met:

1. The arguments are f32.
2. The arguments are loads and they have no uses other than the comparison.
3. The comparison code is EQ or NE.

e.g.
        vldr.32 s0, [r1]
        vldr.32 s1, [r0]
        vcmpe.f32       s1, s0
        vmrs    apsr_nzcv, fpscr
	beq     LBB0_2
=>
        ldr     r1, [r1]
        ldr     r0, [r0]
        cmp     r0, r1
        beq     LBB0_2

More complicated cases will be implemented in subsequent patches.

llvm-svn: 107852

1 files changed, 29 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/ARM/fpcmp-opt.ll b/llvm/test/CodeGen/ARM/fpcmp-opt.ll
new file mode 100644
index 00000000000..ed515cc1e7c
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/fpcmp-opt.ll
@@ -0,0 +1,29 @@
+; RUN: llc < %s -march=arm -mattr=+vfp2 | FileCheck %s
+; rdar://7461510
+
+define arm_apcscc i32 @t1(float* %a, float* %b) nounwind {
+entry:
+; CHECK: t1:
+; CHECK-NOT: vldr
+; CHECK: ldr
+; CHECK: ldr
+; CHECK: cmp r0, r1
+; CHECK-NOT: vcmpe.f32
+; CHECK-NOT: vmrs
+; CHECK: beq
+  %0 = load float* %a
+  %1 = load float* %b
+  %2 = fcmp une float %0, %1
+  br i1 %2, label %bb1, label %bb2
+
+bb1:
+  %3 = call i32 @bar()
+  ret i32 %3
+
+bb2:
+  %4 = call i32 @foo()
+  ret i32 %4
+}
+
+declare i32 @bar()
+declare i32 @foo()