From 79472352526e9b0782accc3bb4686d5193e2970a Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Thu, 6 Nov 2025 11:35:03 +0000
Subject: [PATCH] [X86] narrowBitOpRMW/combineTruncate - don't retain pointer
 info for unknown offset load/stores

#166337 replaces large (illegal type) loads/stores with a smaller i32 load/store based off the demanded shifted bits. As these shifts are non-constant we can't regenerate the PointerInfo data with a fixed offset, so we need to discard the data entirely.

Fixes #166744 - post-ra has to reconstruct dependencies after the chains have been stripped and uses pointer info instead - which resulted in some loads being rescheduled earlier than the dependent store as it was thought they didn't alias
---
 llvm/lib/Target/X86/X86ISelLowering.cpp | 6 ++++--
 llvm/test/CodeGen/X86/pr166744.ll       | 8 ++++----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 4d44227b3ecd4..168e04109a0a5 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -53442,7 +53442,8 @@ static SDValue narrowBitOpRMW(StoreSDNode *St, const SDLoc &DL,
   }
 
   SDValue NewStore =
-      DAG.getStore(St->getChain(), DL, Res, NewPtr, St->getPointerInfo(),
+      DAG.getStore(St->getChain(), DL, Res, NewPtr,
+                   MachinePointerInfo(St->getPointerInfo().getAddrSpace()),
                    Align(), St->getMemOperand()->getFlags());
 
   // If there are other uses of StoredVal, replace with a new load of the
@@ -54639,7 +54640,8 @@ static SDValue combineTruncate(SDNode *N, SelectionDAG &DAG,
         SDValue NewPtr = DAG.getMemBasePlusOffset(
             Ld->getBasePtr(), PtrByteOfs, DL, SDNodeFlags::NoUnsignedWrap);
         SDValue NewLoad =
-            DAG.getLoad(VT, DL, Ld->getChain(), NewPtr, Ld->getPointerInfo(),
+            DAG.getLoad(VT, DL, Ld->getChain(), NewPtr,
+                        MachinePointerInfo(Ld->getPointerInfo().getAddrSpace()),
                         Align(), Ld->getMemOperand()->getFlags());
         DAG.makeEquivalentMemoryOrdering(Ld, NewLoad);
         return NewLoad;
diff --git a/llvm/test/CodeGen/X86/pr166744.ll b/llvm/test/CodeGen/X86/pr166744.ll
index de2a5e6cc78cc..21b25d87796a5 100644
--- a/llvm/test/CodeGen/X86/pr166744.ll
+++ b/llvm/test/CodeGen/X86/pr166744.ll
@@ -3,7 +3,7 @@
 ; RUN: llc < %s -mtriple=x86_64-- -mcpu=haswell | FileCheck %s --check-prefixes=NOPOSTRA
 ; RUN: llc < %s -mtriple=x86_64-- -mcpu=x86-64-v3 | FileCheck %s --check-prefixes=NOPOSTRA
 
-; FIXME: Ensure reloads are after narrowed i512 -> i32 store
+; Ensure reloads are after narrowed i512 -> i32 store
 define i1 @PR166744(ptr %v, i64 %idx, i1 zeroext %b) {
 ; POSTRA-LABEL: PR166744:
 ; POSTRA:       # %bb.0:
@@ -12,15 +12,15 @@ define i1 @PR166744(ptr %v, i64 %idx, i1 zeroext %b) {
 ; POSTRA-NEXT:    bextrl %eax, %esi, %eax
 ; POSTRA-NEXT:    movl (%rdi,%rax,4), %ecx
 ; POSTRA-NEXT:    btrl %esi, %ecx
-; POSTRA-NEXT:    movq 8(%rdi), %rsi
-; POSTRA-NEXT:    orq 40(%rdi), %rsi
 ; POSTRA-NEXT:    orl %ecx, %edx
 ; POSTRA-NEXT:    movl %edx, (%rdi,%rax,4)
 ; POSTRA-NEXT:    movq 16(%rdi), %rax
+; POSTRA-NEXT:    movq (%rdi), %rcx
 ; POSTRA-NEXT:    movq 24(%rdi), %rdx
+; POSTRA-NEXT:    movq 8(%rdi), %rsi
 ; POSTRA-NEXT:    orq 56(%rdi), %rdx
+; POSTRA-NEXT:    orq 40(%rdi), %rsi
 ; POSTRA-NEXT:    orq 48(%rdi), %rax
-; POSTRA-NEXT:    movq (%rdi), %rcx
 ; POSTRA-NEXT:    orq 32(%rdi), %rcx
 ; POSTRA-NEXT:    orq %rdx, %rsi
 ; POSTRA-NEXT:    orq %rax, %rcx