From c3d5cf0bb71f4278ae2e489cefbbe031522e97b3 Mon Sep 17 00:00:00 2001
From: Sanjay Patel <spatel@rotateright.com>
Date: Sun, 2 Jul 2017 14:34:50 +0000
Subject: [PATCH] [InstCombine] look through bswap/bitreverse for equality
 comparisons

I noticed this missed bswap optimization in the CGP memcmp() expansion,
and then I saw that we don't have the fold in InstCombine.

Differential Revision: https://reviews.llvm.org/D34763

llvm-svn: 306980
---
 .../InstCombine/InstCombineCompares.cpp          |  9 +++++++++
 llvm/test/Transforms/InstCombine/icmp.ll         | 16 ++++------------
 2 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 58b8b2f52629..11507ae72b98 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -3438,6 +3438,15 @@ Instruction *InstCombiner::foldICmpEquality(ICmpInst &I) {
     }
   }
 
+  // If both operands are byte-swapped or bit-reversed, just compare the
+  // original values.
+  // TODO: Move this to a function similar to foldICmpIntrinsicWithConstant()
+  // and handle more intrinsics.
+  if ((match(Op0, m_BSwap(m_Value(A))) && match(Op1, m_BSwap(m_Value(B)))) ||
+      (match(Op0, m_Intrinsic<Intrinsic::bitreverse>(m_Value(A))) &&
+       match(Op1, m_Intrinsic<Intrinsic::bitreverse>(m_Value(B)))))
+    return new ICmpInst(Pred, A, B);
+
   return nullptr;
 }
 
diff --git a/llvm/test/Transforms/InstCombine/icmp.ll b/llvm/test/Transforms/InstCombine/icmp.ll
index 127fde10e9f7..a12f4206b1c6 100644
--- a/llvm/test/Transforms/InstCombine/icmp.ll
+++ b/llvm/test/Transforms/InstCombine/icmp.ll
@@ -2979,9 +2979,7 @@ declare i32 @llvm.bswap.i32(i32)
 
 define i1 @bswap_ne(i32 %x, i32 %y) {
 ; CHECK-LABEL: @bswap_ne(
-; CHECK-NEXT:    [[SWAPX:%.*]] = call i32 @llvm.bswap.i32(i32 %x)
-; CHECK-NEXT:    [[SWAPY:%.*]] = call i32 @llvm.bswap.i32(i32 %y)
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[SWAPX]], [[SWAPY]]
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 %x, %y
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %swapx = call i32 @llvm.bswap.i32(i32 %x)
@@ -2994,9 +2992,7 @@ declare <8 x i16> @llvm.bswap.v8i16(<8 x i16>)
 
 define <8 x i1> @bswap_vec_eq(<8 x i16> %x, <8 x i16> %y) {
 ; CHECK-LABEL: @bswap_vec_eq(
-; CHECK-NEXT:    [[SWAPX:%.*]] = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> %x)
-; CHECK-NEXT:    [[SWAPY:%.*]] = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> %y)
-; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <8 x i16> [[SWAPX]], [[SWAPY]]
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq <8 x i16> %x, %y
 ; CHECK-NEXT:    ret <8 x i1> [[CMP]]
 ;
   %swapx = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> %x)
@@ -3009,9 +3005,7 @@ declare i64 @llvm.bitreverse.i64(i64)
 
 define i1 @bitreverse_eq(i64 %x, i64 %y) {
 ; CHECK-LABEL: @bitreverse_eq(
-; CHECK-NEXT:    [[REVX:%.*]] = call i64 @llvm.bitreverse.i64(i64 %x)
-; CHECK-NEXT:    [[REVY:%.*]] = call i64 @llvm.bitreverse.i64(i64 %y)
-; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i64 [[REVX]], [[REVY]]
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i64 %x, %y
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %revx = call i64 @llvm.bitreverse.i64(i64 %x)
@@ -3024,9 +3018,7 @@ declare <8 x i16> @llvm.bitreverse.v8i16(<8 x i16>)
 
 define <8 x i1> @bitreverse_vec_ne(<8 x i16> %x, <8 x i16> %y) {
 ; CHECK-LABEL: @bitreverse_vec_ne(
-; CHECK-NEXT:    [[REVX:%.*]] = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> %x)
-; CHECK-NEXT:    [[REVY:%.*]] = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> %y)
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne <8 x i16> [[REVX]], [[REVY]]
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ne <8 x i16> %x, %y
 ; CHECK-NEXT:    ret <8 x i1> [[CMP]]
 ;
   %revx = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> %x)