[llvm] [LV][EVL] Support cast instruction with EVL-vectorization (PR #108351)

[via llvm-commits]

================
@@ -0,0 +1,659 @@
+; REQUIRES: asserts
+
+; RUN: opt -passes=loop-vectorize -debug-only=loop-vectorize \
+; RUN: -force-tail-folding-style=data-with-evl \
+; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
+; RUN: -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-max=128 -disable-output < %s 2>&1 | FileCheck --check-prefix=IF-EVL %s
+
+; RUN: opt -passes=loop-vectorize -debug-only=loop-vectorize \
+; RUN: -force-tail-folding-style=none \
+; RUN: -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
+; RUN: -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-max=128 -disable-output < %s 2>&1 | FileCheck --check-prefix=NO-VP %s
+
+define void @vp_sext(ptr noalias %a, ptr noalias %b, i64 %N) {
+; IF-EVL: VPlan 'Final VPlan for VF={vscale x 1,vscale x 2},UF={1}' {
+; IF-EVL-NEXT: Live-in vp<%0> = VF * UF
+; IF-EVL-NEXT: Live-in vp<%1> = vector-trip-count
+; IF-EVL-NEXT: Live-in ir<%N> = original trip-count
+
+; IF-EVL: vector.ph:
+; IF-EVL-NEXT: Successor(s): vector loop
+
+; IF-EVL: <x1> vector loop: {
+; IF-EVL-NEXT:  vector.body:
+; IF-EVL-NEXT:    EMIT vp<%3> = CANONICAL-INDUCTION ir<0>, vp<%11>
+; IF-EVL-NEXT:    EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI vp<%4> = phi ir<0>, vp<%10>
+; IF-EVL-NEXT:    EMIT vp<%5> = EXPLICIT-VECTOR-LENGTH vp<%4>, ir<%N>
+; IF-EVL-NEXT:    vp<%6> = SCALAR-STEPS vp<%4>, ir<1>
+; IF-EVL-NEXT:    CLONE ir<%arrayidx> = getelementptr inbounds ir<%b>, vp<%6>
+; IF-EVL-NEXT:    vp<%7> = vector-pointer ir<%arrayidx>
+; IF-EVL-NEXT:    WIDEN ir<%0> = vp.load vp<%7>, vp<%5>
+; IF-EVL-NEXT:    WIDEN-CAST ir<%conv2> = vp.sext ir<%0>, vp<%5>
+; IF-EVL-NEXT:    CLONE ir<%arrayidx4> = getelementptr inbounds ir<%a>, vp<%6>
+; IF-EVL-NEXT:    vp<%8> = vector-pointer ir<%arrayidx4>
+; IF-EVL-NEXT:    WIDEN vp.store vp<%8>, ir<%conv2>, vp<%5>
+; IF-EVL-NEXT:    SCALAR-CAST vp<%9> = zext vp<%5> to i64
+; IF-EVL-NEXT:    EMIT vp<%10> = add vp<%9>, vp<%4>
+; IF-EVL-NEXT:    EMIT vp<%11> = add vp<%3>, vp<%0>
+; IF-EVL-NEXT:    EMIT branch-on-count vp<%11>, vp<%1>
+; IF-EVL-NEXT:  No successors
+; IF-EVL-NEXT: }
+
+; NO-VP: VPlan 'Final VPlan for VF={vscale x 1,vscale x 2},UF>=1' {
+; NO-VP-NEXT: Live-in vp<%0> = VF * UF
+; NO-VP-NEXT: Live-in vp<%1> = vector-trip-count
+; NO-VP-NEXT: Live-in ir<%N> = original trip-count
+ 
+; NO-VP: vector.ph:
+; NO-VP-NEXT: Successor(s): vector loop
+
+; NO-VP: <x1> vector loop: {
+; NO-VP-NEXT:   vector.body:
+; NO-VP-NEXT:     EMIT vp<%2> = CANONICAL-INDUCTION ir<0>, vp<%6>
+; NO-VP-NEXT:     vp<%3> = SCALAR-STEPS vp<%2>, ir<1>
+; NO-VP-NEXT:     CLONE ir<%arrayidx> = getelementptr inbounds ir<%b>, vp<%3>
+; NO-VP-NEXT:     vp<%4> = vector-pointer ir<%arrayidx>
+; NO-VP-NEXT:     WIDEN ir<%0> = load vp<%4>
+; NO-VP-NEXT:     WIDEN-CAST ir<%conv2> = sext ir<%0> to i64
+; NO-VP-NEXT:     CLONE ir<%arrayidx4> = getelementptr inbounds ir<%a>, vp<%3>
+; NO-VP-NEXT:     vp<%5> = vector-pointer ir<%arrayidx4>
+; NO-VP-NEXT:     WIDEN store vp<%5>, ir<%conv2>
+; NO-VP-NEXT:     EMIT vp<%6> = add nuw vp<%2>, vp<%0>
+; NO-VP-NEXT:     EMIT branch-on-count vp<%6>, vp<%1>
+; NO-VP-NEXT:   No successors
+; NO-VP-NEXT: }
+
+entry:
+  %cmp8 = icmp sgt i64 %N, 0
+  br i1 %cmp8, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
----------------
LiqinWeng wrote:

done

https://github.com/llvm/llvm-project/pull/108351