[llvm] 1bdc6ea - [LoopLoadElim] Support opaque pointers

[Arthur Eubanks via llvm-commits]

Author: Arthur Eubanks
Date: 2022-02-09T09:22:21-08:00
New Revision: 1bdc6eacba43c42016ac5d5f2edfd61d2867fb90

URL: https://github.com/llvm/llvm-project/commit/1bdc6eacba43c42016ac5d5f2edfd61d2867fb90
DIFF: https://github.com/llvm/llvm-project/commit/1bdc6eacba43c42016ac5d5f2edfd61d2867fb90.diff

LOG: [LoopLoadElim] Support opaque pointers

With typed pointers the pointer operand type checks the address space
and the load/store type. With opaque pointers we have to check the
load/store type separately.

Added: 
    llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll

Modified: 
    llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp b/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
index 21d59936616b5..307d0b17a041d 100644
--- a/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
@@ -213,7 +213,8 @@ class LoadEliminationForLoop {
         continue;
 
       // Only progagate the value if they are of the same type.
-      if (Store->getPointerOperandType() != Load->getPointerOperandType())
+      if (Store->getPointerOperandType() != Load->getPointerOperandType() ||
+          getLoadStoreType(Store) != getLoadStoreType(Load))
         continue;
 
       Candidates.emplace_front(Load, Store);

diff  --git a/llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll b/llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll
new file mode 100644
index 0000000000000..126805462ab11
--- /dev/null
+++ b/llvm/test/Transforms/LoopLoadElim/type-mismatch-opaque-ptr.ll
@@ -0,0 +1,87 @@
+; RUN: opt --opaque-pointers -loop-load-elim -S < %s | FileCheck %s
+
+; Don't crash if the store and the load use 
diff erent types.
+;
+;   for (unsigned i = 0; i < 100; i++) {
+;     A[i+1] = B[i] + 2;
+;     C[i] = ((float*)A)[i] * 2;
+;   }
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; CHECK-LABEL: @f(
+define void @f(ptr noalias %A, ptr noalias %B, ptr noalias %C, i64 %N) {
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+
+  %Aidx_next = getelementptr inbounds i32, ptr %A, i64 %indvars.iv.next
+  %Bidx = getelementptr inbounds i32, ptr %B, i64 %indvars.iv
+  %Cidx = getelementptr inbounds i32, ptr %C, i64 %indvars.iv
+  %Aidx = getelementptr inbounds i32, ptr %A, i64 %indvars.iv
+
+  %b = load i32, ptr %Bidx, align 4
+  %a_p1 = add i32 %b, 2
+  store i32 %a_p1, ptr %Aidx_next, align 4
+
+; CHECK: %a = load float, ptr %Aidx, align 4
+  %a = load float, ptr %Aidx, align 4
+; CHECK-NEXT: %c = fmul float %a, 2.0
+  %c = fmul float %a, 2.0
+  %c.int = fptosi float %c to i32
+  store i32 %c.int, ptr %Cidx, align 4
+
+  %exitcond = icmp eq i64 %indvars.iv.next, %N
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+; Don't crash if the store and the load use 
diff erent types.
+;
+;   for (unsigned i = 0; i < 100; i++) {
+;     A[i+1] = B[i] + 2;
+;     A[i+1] = B[i] + 3;
+;     C[i] = ((float*)A)[i] * 2;
+;   }
+
+; CHECK-LABEL: @f2(
+define void @f2(ptr noalias %A, ptr noalias %B, ptr noalias %C, i64 %N) {
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+
+  %Aidx_next = getelementptr inbounds i32, ptr %A, i64 %indvars.iv.next
+  %Bidx = getelementptr inbounds i32, ptr %B, i64 %indvars.iv
+  %Cidx = getelementptr inbounds i32, ptr %C, i64 %indvars.iv
+  %Aidx = getelementptr inbounds i32, ptr %A, i64 %indvars.iv
+
+  %b = load i32, ptr %Bidx, align 4
+  %a_p2 = add i32 %b, 2
+  store i32 %a_p2, ptr %Aidx_next, align 4
+
+  %a_p3 = add i32 %b, 3
+  store i32 %a_p3, ptr %Aidx_next, align 4
+
+; CHECK: %a = load float, ptr %Aidx, align 4
+  %a = load float, ptr %Aidx, align 4
+; CHECK-NEXT: %c = fmul float %a, 2.0
+  %c = fmul float %a, 2.0
+  %c.int = fptosi float %c to i32
+  store i32 %c.int, ptr %Cidx, align 4
+
+  %exitcond = icmp eq i64 %indvars.iv.next, %N
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}