From 9e3e1aad3161f4ce5301c3a59c7313ad83240a6d Mon Sep 17 00:00:00 2001
From: Srividya Karumuri <srividya_karumuri@apple.com>
Date: Mon, 29 Nov 2021 16:25:21 -0800
Subject: [PATCH] [InstCombine] Allow fake vector insert folding to bit-logic
 only if the insert element is integer type

The below commit is causing assertion when insert element type is not integer
 type such as half. This is because the transformation is creating zext before
 doing bitwise OR, and the zext is supported only for integer types
https://github.com/llvm/llvm-project/commit/80ab06c599a0f5a90951c36a57b2a9b492b19d61

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D114734
---
 .../InstCombine/InstCombineCasts.cpp          |  2 +-
 .../InstCombine/bitcast-inselt-bitcast.ll     | 23 +++++++++++++++++++
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
index ca87477c5d81..33f217659c01 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -2771,7 +2771,7 @@ Instruction *InstCombinerImpl::visitBitCast(BitCastInst &CI) {
     if (match(Src, m_OneUse(m_InsertElt(m_OneUse(m_BitCast(m_Value(X))),
                                         m_Value(Y), m_ConstantInt(IndexC)))) &&
         DestTy->isIntegerTy() && X->getType() == DestTy &&
-        isDesirableIntType(BitWidth)) {
+        Y->getType()->isIntegerTy() && isDesirableIntType(BitWidth)) {
       // Adjust for big endian - the LSBs are at the high index.
       if (DL.isBigEndian())
         IndexC = SrcVTy->getNumElements() - 1 - IndexC;
diff --git a/llvm/test/Transforms/InstCombine/bitcast-inselt-bitcast.ll b/llvm/test/Transforms/InstCombine/bitcast-inselt-bitcast.ll
index 464a438f286f..c60f8028d72e 100644
--- a/llvm/test/Transforms/InstCombine/bitcast-inselt-bitcast.ll
+++ b/llvm/test/Transforms/InstCombine/bitcast-inselt-bitcast.ll
@@ -70,6 +70,29 @@ define i32 @insert0_v4i8(i32 %x, i8 %y) {
   ret i32 %r
 }
 
+; i32 is a common type, so we can convert independently of the data layout.
+; Endian determines if a shift is needed (and so the transform is avoided).
+; half type can not be used in zext instruction (and so the transform is avoided).
+
+define i32 @insert0_v2half(i32 %x, half %y) {
+; BE-LABEL: @insert0_v2half(
+; BE-NEXT:    [[V:%.*]] = bitcast i32 [[X:%.*]] to <2 x half>
+; BE-NEXT:    [[I:%.*]] = insertelement <2 x half> [[V]], half [[Y:%.*]], i8 0
+; BE-NEXT:    [[R:%.*]] = bitcast <2 x half> [[I]] to i32
+; BE-NEXT:    ret i32 [[R]]
+;
+; LE-LABEL: @insert0_v2half(
+; LE-NEXT:    [[V:%.*]] = bitcast i32 [[X:%.*]] to <2 x half>
+; LE-NEXT:    [[I:%.*]] = insertelement <2 x half> [[V]], half [[Y:%.*]], i8 0
+; LE-NEXT:    [[R:%.*]] = bitcast <2 x half> [[I]] to i32
+; LE-NEXT:    ret i32 [[R]]
+;
+  %v = bitcast i32 %x to <2 x half>
+  %i = insertelement <2 x half> %v, half %y, i8 0
+  %r = bitcast <2 x half> %i to i32
+  ret i32 %r
+}
+
 ; i64 is a legal type, so we can convert based on the data layout.
 ; Endian determines if a shift is needed (and so the transform is avoided).