[X86] Do not lower scalar sdiv/udiv to a shifts + mul sequence when optimizing for minsize

There are some cases where the mul sequence is smaller, but for the most part,
using a div is preferable. This does not apply to vectors, since x86 doesn't
have vector idiv, and a vector mul/shifts sequence ought to be smaller than a
scalarized division.

Differential Revision: http://reviews.llvm.org/D12082

llvm-svn: 245431

2 files changed, 45 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/divide-by-constant.ll b/llvm/test/CodeGen/X86/divide-by-constant.ll
index fd07a3f5510..9543d6c4d74 100644
--- a/llvm/test/CodeGen/X86/divide-by-constant.ll
+++ b/llvm/test/CodeGen/X86/divide-by-constant.ll
@@ -94,3 +94,35 @@ define i8 @test9(i8 %x) nounwind {
 ; CHECK: shrl $11
 ; CHECK: ret
 }
+
+define i32 @testsize1(i32 %x) minsize nounwind {
+entry:
+	%div = sdiv i32 %x, 32
+	ret i32 %div
+; CHECK-LABEL: testsize1:
+; CHECK: divl
+}
+
+define i32 @testsize2(i32 %x) minsize nounwind {
+entry:
+	%div = sdiv i32 %x, 33
+	ret i32 %div
+; CHECK-LABEL: testsize2:
+; CHECK: divl
+}
+
+define i32 @testsize3(i32 %x) minsize nounwind {
+entry:
+	%div = udiv i32 %x, 32
+	ret i32 %div
+; CHECK-LABEL: testsize3:
+; CHECK: shrl
+}
+
+define i32 @testsize4(i32 %x) minsize nounwind {
+entry:
+	%div = udiv i32 %x, 33
+	ret i32 %div
+; CHECK-LABEL: testsize4:
+; CHECK: divl
+}
diff --git a/llvm/test/CodeGen/X86/vec_sdiv_to_shift.ll b/llvm/test/CodeGen/X86/vec_sdiv_to_shift.ll
index 56855d3c44e..7f71a0c2ea5 100644
--- a/llvm/test/CodeGen/X86/vec_sdiv_to_shift.ll
+++ b/llvm/test/CodeGen/X86/vec_sdiv_to_shift.ll
@@ -13,6 +13,19 @@ entry:
   ret <8 x i16> %0
 }
 
+define <8 x i16> @sdiv_vec8x16_minsize(<8 x i16> %var) minsize {
+entry:
+; CHECK: sdiv_vec8x16_minsize
+; CHECK: psraw  $15
+; CHECK: vpsrlw  $11
+; CHECK: vpaddw
+; CHECK: vpsraw  $5
+; CHECK: ret
+  %0 = sdiv <8 x i16> %var, <i16 32, i16 32, i16 32, i16 32, i16 32, i16 32, i16 32, i16 32>
+  ret <8 x i16> %0
+}
+
+
 define <4 x i32> @sdiv_zero(<4 x i32> %var) {
 entry:
 ; CHECK: sdiv_zero