[llvm] 4c399b2 - [LV] Add select cost test with negated condition. (NFC)

[Florian Hahn via llvm-commits]

Author: Florian Hahn
Date: 2025-12-18T22:07:06Z
New Revision: 4c399b27c321aee0888bcbfc919ff036fad180a9

URL: https://github.com/llvm/llvm-project/commit/4c399b27c321aee0888bcbfc919ff036fad180a9
DIFF: https://github.com/llvm/llvm-project/commit/4c399b27c321aee0888bcbfc919ff036fad180a9.diff

LOG: [LV] Add select cost test with negated condition. (NFC)

Add additional test coverage for select with negated condition.
Currently we overestimate the cost, because the negation can be folded
in the compare.

Added: 
    

Modified: 
    llvm/test/Transforms/LoopVectorize/AArch64/select-costs.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/Transforms/LoopVectorize/AArch64/select-costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/select-costs.ll
index 20409f66fc51f..7fcfcf05b89ca 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/select-costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/select-costs.ll
@@ -18,16 +18,12 @@ define void @selects_1(ptr nocapture %dst, i32 %A, i32 %B, i32 %C, i32 %N) {
 ; CHECK: LV: Selecting VF: 4
 
 entry:
-  %cmp26 = icmp sgt i32 %N, 0
-  br i1 %cmp26, label %for.body.preheader, label %for.cond.cleanup
-
-for.body.preheader:                               ; preds = %entry
   %n = zext i32 %N to i64
-  br label %for.body
+  br label %loop
 
-for.body:                                         ; preds = %for.body.preheader, %for.body
-  %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
-  %arrayidx = getelementptr inbounds i32, ptr %dst, i64 %indvars.iv
+loop:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+  %arrayidx = getelementptr inbounds i32, ptr %dst, i64 %iv
   %0 = load i32, ptr %arrayidx, align 4
   %and = and i32 %0, 2047
   %cmp1 = icmp eq i32 %and, %A
@@ -37,14 +33,11 @@ for.body:                                         ; preds = %for.body.preheader,
   %cmp7 = icmp ugt i32 %cond, %C
   %cond11 = select i1 %cmp7, i32 %cond, i32 %cond6
   store i32 %cond11, ptr %arrayidx, align 4
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond.not = icmp eq i64 %indvars.iv.next, %n
-  br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body
-
-for.cond.cleanup.loopexit:                        ; preds = %for.body
-  br label %for.cond.cleanup
+  %iv.next = add nuw nsw i64 %iv, 1
+  %ec = icmp eq i64 %iv.next, %n
+  br i1 %ec, label %exit, label %loop
 
-for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
+exit:
   ret void
 }
 
@@ -53,20 +46,20 @@ define i32 @multi_user_cmp(ptr readonly %a, i64 noundef %n) {
 ; CHECK: Cost of 4 for VF 16: WIDEN ir<%cmp1> = fcmp olt ir<%load1>, ir<0.000000e+00>
 ; CHECK: LV: Selecting VF: 16.
 entry:
-  br label %for.body
+  br label %loop
 
-for.body:
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
-  %all.off.next = phi i1 [ true, %entry ], [ %all.off, %for.body ]
-  %any.0.off09 = phi i1 [ false, %entry ], [ %.any.0.off0, %for.body ]
-  %arrayidx = getelementptr inbounds float, ptr %a, i64 %indvars.iv
+loop:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+  %all.off.next = phi i1 [ true, %entry ], [ %all.off, %loop ]
+  %any.0.off09 = phi i1 [ false, %entry ], [ %.any.0.off0, %loop ]
+  %arrayidx = getelementptr inbounds float, ptr %a, i64 %iv
   %load1 = load float, ptr %arrayidx, align 4
   %cmp1 = fcmp olt float %load1, 0.000000e+00
   %.any.0.off0 = select i1 %cmp1, i1 true, i1 %any.0.off09
   %all.off = select i1 %cmp1, i1 %all.off.next, i1 false
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond.not = icmp eq i64 %indvars.iv.next, %n
-  br i1 %exitcond.not, label %exit, label %for.body
+  %iv.next = add nuw nsw i64 %iv, 1
+  %ec = icmp eq i64 %iv.next, %n
+  br i1 %ec, label %exit, label %loop
 
 exit:
   %0 = select i1 %.any.0.off0, i32 2, i32 3
@@ -96,3 +89,33 @@ loop:
 exit:
   ret i32 %red.next
 }
+
+define i32 @select_xor_cond(ptr %src, i1 %c.0) {
+; CHECK: LV: Checking a loop in 'select_xor_cond'
+; CHECK: Cost of 6 for VF 2: WIDEN-SELECT ir<%sel> = select ir<%c>, ir<false>, ir<%c.0>
+; CHECK: Cost of 12 for VF 4: WIDEN-SELECT ir<%sel> = select ir<%c>, ir<false>, ir<%c.0>
+; CHECK: Cost of 24 for VF 8: WIDEN-SELECT ir<%sel> = select ir<%c>, ir<false>, ir<%c.0>
+; CHECK: Cost of 48 for VF 16: WIDEN-SELECT ir<%sel> = select ir<%c>, ir<false>, ir<%c.0>
+; CHECK: LV: Selecting VF: 4.
+
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+  %p = phi i32 [ 0, %entry ], [ %ext.sel, %loop ]
+  %gep.src = getelementptr i8, ptr %src, i64 %iv
+  %0 = load i8, ptr %gep.src, align 1
+  %c = icmp eq i8 %0, 0
+  %not.c = xor i1 %c, true
+  %sel = select i1 %not.c, i1 %c.0, i1 false
+  %ext.sel = zext i1 %sel to i32
+  %iv.next = add i64 %iv, 1
+  %ec = icmp eq i64 %iv, 19
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  %ext.c = zext i1 %c to i32
+  %res = add i32 %ext.c, %p
+  ret i32 %res
+}