Convert floating point division by a constant into multiplication by the

reciprocal if converting to the reciprocal is exact.  Do it even if inexact
if -ffast-math.  This substantially speeds up ac.f90 from the polyhedron
benchmarks.

llvm-svn: 154265

2 files changed, 38 insertions, 6 deletions

diff --git a/llvm/test/CodeGen/ARM/vdiv_combine.ll b/llvm/test/CodeGen/ARM/vdiv_combine.ll
index 13873932abd..7fddbed1ed5 100644
--- a/llvm/test/CodeGen/ARM/vdiv_combine.ll
+++ b/llvm/test/CodeGen/ARM/vdiv_combine.ll
@@ -8,7 +8,7 @@ declare void @foo_int32x4_t(<4 x i32>)
 
 ; Test signed conversion.
 ; CHECK: t1
-; CHECK-NOT: vdiv
+; CHECK-NOT: {{vdiv|vmul}}
 define void @t1() nounwind {
 entry:
   %tmp = load i32* @iin, align 4, !tbaa !3
@@ -24,7 +24,7 @@ declare void @foo_float32x2_t(<2 x float>)
 
 ; Test unsigned conversion.
 ; CHECK: t2
-; CHECK-NOT: vdiv
+; CHECK-NOT: {{vdiv|vmul}}
 define void @t2() nounwind {
 entry:
   %tmp = load i32* @uin, align 4, !tbaa !3
@@ -38,7 +38,7 @@ entry:
 
 ; Test which should not fold due to non-power of 2.
 ; CHECK: t3
-; CHECK: vdiv
+; CHECK: {{vdiv|vmul}}
 define void @t3() nounwind {
 entry:
   %tmp = load i32* @iin, align 4, !tbaa !3
@@ -52,7 +52,7 @@ entry:
 
 ; Test which should not fold due to power of 2 out of range.
 ; CHECK: t4
-; CHECK: vdiv
+; CHECK: {{vdiv|vmul}}
 define void @t4() nounwind {
 entry:
   %tmp = load i32* @iin, align 4, !tbaa !3
@@ -66,7 +66,7 @@ entry:
 
 ; Test case where const is max power of 2 (i.e., 2^32).
 ; CHECK: t5
-; CHECK-NOT: vdiv
+; CHECK-NOT: {{vdiv|vmul}}
 define void @t5() nounwind {
 entry:
   %tmp = load i32* @iin, align 4, !tbaa !3
@@ -80,7 +80,7 @@ entry:
 
 ; Test quadword.
 ; CHECK: t6
-; CHECK-NOT: vdiv
+; CHECK-NOT: {{vdiv|vmul}}
 define void @t6() nounwind {
 entry:
   %tmp = load i32* @iin, align 4, !tbaa !3
diff --git a/llvm/test/CodeGen/X86/fdiv.ll b/llvm/test/CodeGen/X86/fdiv.ll
new file mode 100644
index 00000000000..553f14efa13
--- /dev/null
+++ b/llvm/test/CodeGen/X86/fdiv.ll
@@ -0,0 +1,32 @@
+; RUN: llc < %s -march=x86-64 | FileCheck %s
+; RUN: llc < %s -march=x86-64 -enable-unsafe-fp-math | FileCheck -check-prefix=UNSAFE %s
+
+define double @exact(double %x) {
+; Exact division by a constant always converted to multiplication.
+; CHECK: @exact
+; CHECK: mulsd
+; UNSAFE: @exact
+; UNSAFE: mulsd
+  %div = fdiv double %x, 2.0
+  ret double %div
+}
+
+define double @inexact(double %x) {
+; Inexact division by a constant converted to multiplication if unsafe-math.
+; CHECK: @inexact
+; CHECK: divsd
+; UNSAFE: @inexact
+; UNSAFE: mulsd
+  %div = fdiv double %x, 0x41DFFFFFFFC00000 
+  ret double %div
+}
+
+define double @funky(double %x) {
+; No conversion to multiplication if too funky.
+; CHECK: @funky
+; CHECK: divsd
+; UNSAFE: @funky
+; UNSAFE: divsd
+  %div = fdiv double %x, 0.0
+  ret double %div
+}