[LSR] Precommit test for D132443

[eopXD]

Summary

Pre-commit test for D132443

[eopXD]

Simplify the testcase even more.

[eopXD]

Update comments in testcases.

[craig.topper]

llvm/test/Transforms/LoopStrengthReduce/lsr-fold-iv-complicate-add-rec.ll

2 ↗

(On Diff #455487)

Move the RUN line above this description

llvm/test/Transforms/LoopStrengthReduce/lsr-fold-iv-const-tripcount.ll

2 ↗

(On Diff #455487)

Move the RUN line above this description

llvm/test/Transforms/LoopStrengthReduce/lsr-fold-iv-runtime-tripcount.ll

2 ↗

(On Diff #455487)

Same

[fhahn]

llvm/test/Transforms/LoopStrengthReduce/lsr-fold-iv-runtime-tripcount.ll

84 ↗

(On Diff #455487)

is all those here really needed?

93 ↗

(On Diff #455487)

is all this here really needed?

112 ↗

(On Diff #455487)

is all those here really needed?

[eopXD]

Simplify the testcase. Move RUN to above.

[fhahn]

Thanks for the update! Given hat all those tests seem to be slight variations of each other, should they be moved in the same file, with a comment highlighting the differences, which are mostly the trip count and/or the complexity of the addrec

llvm/test/Transforms/LoopStrengthReduce/lsr-fold-iv-complicate-add-rec.ll

36 ↗

(On Diff #456124)

nit: easier to right if the exit block is at the end.

llvm/test/Transforms/LoopStrengthReduce/lsr-fold-iv-runtime-tripcount.ll

45 ↗

(On Diff #456124)

is this needed? Could we not have a simple variant of /lsr-fold-iv-complicate-add-rec.ll where the incoming value is something like [ %N, %entry ] instead of [ 379, %entry ]?

[eopXD]

Address comments from @fhahn

• Merge 3 testcases into a single file
• Simplify testcase for runtime tripcount

[eopXD]

Rename testcase.

[eopXD]

Gentle ping, thank you.

[fhahn]

In D132452#3769081, @eopXD wrote:

Gentle ping, thank you.

as mentioned in D132443, it seems like more negative test coverage would be good.

llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll

58

Nit: looks like a type ->ruin -> run :)

[eopXD]

Fix minor type-o.

[craig.topper]

LGTM

llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes="loop-reduce" -S | FileCheck %s
+
+; There are 3 test cases here regarding the replacing the primary iv with
+; other affine AddRec IV.
+; 1. Loop with constant tripcount
+; 2. Loop with runtime tripcount
+; 3. The replacing AddRec IV is a complicated AddRec. This tests whether
+;    the fold terminating condition transformation is writing new terminating
+;    condition in the correct type.
+
+target datalayout = "e-p:32:32:32-n32"
+
+; This is equivalent to the following code, loop guard is removed.
+;   void const_tripcount(int *a) {
+;     for (int i = 21; i < 400; i++)
+;       a[i] = 1;
+;   }
+define void @const_tripcount(ptr %a) {
+; CHECK-LABEL: @const_tripcount(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[UGLYGEP:%.*]] = getelementptr i8, ptr [[A:%.*]], i64 84
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[LSR_IV1:%.*]] = phi ptr [ [[UGLYGEP2:%.*]], [[FOR_BODY]] ], [ [[UGLYGEP]], [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[LSR_IV:%.*]] = phi i64 [ [[LSR_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 379, [[ENTRY]] ]
+; CHECK-NEXT:    store i32 1, ptr [[LSR_IV1]], align 4
+; CHECK-NEXT:    [[LSR_IV_NEXT]] = add nsw i64 [[LSR_IV]], -1
+; CHECK-NEXT:    [[UGLYGEP2]] = getelementptr i8, ptr [[LSR_IV1]], i64 4
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[LSR_IV_NEXT]], 0
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %uglygep = getelementptr i8, ptr %a, i64 84
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %lsr.iv1 = phi ptr [ %uglygep2, %for.body ], [ %uglygep, %entry ]
+  %lsr.iv = phi i64 [ %lsr.iv.next, %for.body ], [ 379, %entry ]
+  store i32 1, ptr %lsr.iv1, align 4
+  %lsr.iv.next = add nsw i64 %lsr.iv, -1
+  %uglygep2 = getelementptr i8, ptr %lsr.iv1, i64 4
+  %exitcond.not = icmp eq i64 %lsr.iv.next, 0
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+; This is equivalent to the following code, loop guard is removed.
+;   void runtime_tripcount(int *a, int N) {
+;     for (int i = 21; i < N; i++)
+;       a[i] = 1;
+;   }
+
+define void @ruintime_tripcount(ptr %a, i32 %N) {
+; CHECK-LABEL: @ruintime_tripcount(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[UGLYGEP:%.*]] = getelementptr i8, ptr [[A:%.*]], i32 84
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[LSR_IV1:%.*]] = phi ptr [ [[UGLYGEP2:%.*]], [[FOR_BODY]] ], [ [[UGLYGEP]], [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[N:%.*]], [[ENTRY]] ]
+; CHECK-NEXT:    store i32 1, ptr [[LSR_IV1]], align 4
+; CHECK-NEXT:    [[LSR_IV_NEXT]] = add nsw i32 [[LSR_IV]], -1
+; CHECK-NEXT:    [[UGLYGEP2]] = getelementptr i8, ptr [[LSR_IV1]], i64 4
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[LSR_IV_NEXT]], 0
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %uglygep = getelementptr i8, ptr %a, i32 84
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %lsr.iv1 = phi ptr [ %uglygep2, %for.body ], [ %uglygep, %entry ]
+  %lsr.iv = phi i32 [ %lsr.iv.next, %for.body ], [ %N, %entry ]
+  store i32 1, ptr %lsr.iv1, align 4
+  %lsr.iv.next = add nsw i32 %lsr.iv, -1
+  %uglygep2 = getelementptr i8, ptr %lsr.iv1, i64 4
+  %exitcond.not = icmp eq i32 %lsr.iv.next, 0
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+; This is modified from IR of the following code, loop guard is removed.
+;   void foo(int*);
+;   void ptr_of_ptr_addrec(int **ptrptr, int length) {
+;     int **it = ptrptr;
+;       for (int i = length; i; i--) {
+;           foo(*it);
+;           it++;
+;       }
+;   }
+define void @ptr_of_ptr_addrec(ptr %ptrptr, i32 %length) {
+; CHECK-LABEL: @ptr_of_ptr_addrec(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[START_PTRPTR:%.*]] = getelementptr inbounds ptr, ptr [[PTRPTR:%.*]]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_05:%.*]] = phi i32 [ [[DEC:%.*]], [[FOR_BODY]] ], [ [[LENGTH:%.*]], [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[IT_04:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ], [ [[START_PTRPTR]], [[ENTRY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[IT_04]], align 8
+; CHECK-NEXT:    tail call void @foo(ptr [[TMP0]])
+; CHECK-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds ptr, ptr [[IT_04]], i64 1
+; CHECK-NEXT:    [[DEC]] = add i32 [[I_05]], -1
+; CHECK-NEXT:    [[TOBOOL_NOT:%.*]] = icmp eq i32 [[DEC]], 0
+; CHECK-NEXT:    br i1 [[TOBOOL_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %start.ptrptr = getelementptr inbounds ptr, ptr %ptrptr
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %i.05 = phi i32 [ %dec, %for.body ], [ %length, %entry ]
+  %it.04 = phi ptr [ %incdec.ptr, %for.body ], [ %start.ptrptr, %entry ]
+  %0 = load ptr, ptr %it.04, align 8
+  tail call void @foo(ptr %0)
+  %incdec.ptr = getelementptr inbounds ptr, ptr %it.04, i64 1
+  %dec = add nsw i32 %i.05, -1
+  %tobool.not = icmp eq i32 %dec, 0
+  br i1 %tobool.not, label %for.end, label %for.body
+
+for.end:                                 ; preds = %for.body
+  ret void
+}
+
+declare void @foo(ptr)