SLP cannot vectorize frem calls in AArch64.

It needs updated costs when there are available vector library functions
given the VF and type.

Author: paschalis-mpeis

llvm/test/Transforms/SLPVectorizer/AArch64/slp-frem.ll

@@ -0,0 +1,71 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt < %s -S -mtriple=aarch64 -vector-library=ArmPL -passes=slp-vectorizer | FileCheck %s
+
+@a = common global ptr null, align 8
+
+define void @frem_v2double() {
+; CHECK-LABEL: define void @frem_v2double() {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[A0:%.*]] = load double, ptr @a, align 8
+; CHECK-NEXT:    [[A1:%.*]] = load double, ptr getelementptr inbounds (double, ptr @a, i64 1), align 8
+; CHECK-NEXT:    [[B0:%.*]] = load double, ptr @a, align 8
+; CHECK-NEXT:    [[B1:%.*]] = load double, ptr getelementptr inbounds (double, ptr @a, i64 1), align 8
+; CHECK-NEXT:    [[R0:%.*]] = frem double [[A0]], [[B0]]
+; CHECK-NEXT:    [[R1:%.*]] = frem double [[A1]], [[B1]]
+; CHECK-NEXT:    store double [[R0]], ptr @a, align 8
+; CHECK-NEXT:    store double [[R1]], ptr getelementptr inbounds (double, ptr @a, i64 1), align 8
+; CHECK-NEXT:    ret void
+;
+entry:
+  %a0 = load double, ptr getelementptr inbounds (double, ptr @a, i64 0), align 8
+  %a1 = load double, ptr getelementptr inbounds (double, ptr @a, i64 1), align 8
+  %b0 = load double, ptr getelementptr inbounds (double, ptr @a, i64 0), align 8
+  %b1 = load double, ptr getelementptr inbounds (double, ptr @a, i64 1), align 8
+  %r0 = frem double %a0, %b0
+  %r1 = frem double %a1, %b1
+  store double %r0, ptr getelementptr inbounds (double, ptr @a, i64 0), align 8
+  store double %r1, ptr getelementptr inbounds (double, ptr @a, i64 1), align 8
+  ret void
+}
+
+define void @frem_v4float() {
+; CHECK-LABEL: define void @frem_v4float() {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[A0:%.*]] = load float, ptr @a, align 8
+; CHECK-NEXT:    [[A1:%.*]] = load float, ptr getelementptr inbounds (float, ptr @a, i64 1), align 8
+; CHECK-NEXT:    [[A2:%.*]] = load float, ptr getelementptr inbounds (float, ptr @a, i64 2), align 8
+; CHECK-NEXT:    [[A3:%.*]] = load float, ptr getelementptr inbounds (float, ptr @a, i64 3), align 8
+; CHECK-NEXT:    [[B0:%.*]] = load float, ptr @a, align 8
+; CHECK-NEXT:    [[B1:%.*]] = load float, ptr getelementptr inbounds (float, ptr @a, i64 1), align 8
+; CHECK-NEXT:    [[B2:%.*]] = load float, ptr getelementptr inbounds (float, ptr @a, i64 2), align 8
+; CHECK-NEXT:    [[B3:%.*]] = load float, ptr getelementptr inbounds (float, ptr @a, i64 3), align 8
+; CHECK-NEXT:    [[R0:%.*]] = frem float [[A0]], [[B0]]
+; CHECK-NEXT:    [[R1:%.*]] = frem float [[A1]], [[B1]]
+; CHECK-NEXT:    [[R2:%.*]] = frem float [[A2]], [[B2]]
+; CHECK-NEXT:    [[R3:%.*]] = frem float [[A3]], [[B3]]
+; CHECK-NEXT:    store float [[R0]], ptr @a, align 8
+; CHECK-NEXT:    store float [[R1]], ptr getelementptr inbounds (float, ptr @a, i64 1), align 8
+; CHECK-NEXT:    store float [[R2]], ptr getelementptr inbounds (float, ptr @a, i64 2), align 8
+; CHECK-NEXT:    store float [[R3]], ptr getelementptr inbounds (float, ptr @a, i64 3), align 8
+; CHECK-NEXT:    ret void
+;
+entry:
+  %a0 = load float, ptr getelementptr inbounds (float, ptr @a, i64 0), align 8
+  %a1 = load float, ptr getelementptr inbounds (float, ptr @a, i64 1), align 8
+  %a2 = load float, ptr getelementptr inbounds (float, ptr @a, i64 2), align 8
+  %a3 = load float, ptr getelementptr inbounds (float, ptr @a, i64 3), align 8
+  %b0 = load float, ptr getelementptr inbounds (float, ptr @a, i64 0), align 8
+  %b1 = load float, ptr getelementptr inbounds (float, ptr @a, i64 1), align 8
+  %b2 = load float, ptr getelementptr inbounds (float, ptr @a, i64 2), align 8
+  %b3 = load float, ptr getelementptr inbounds (float, ptr @a, i64 3), align 8
+  %r0 = frem float %a0, %b0
+  %r1 = frem float %a1, %b1
+  %r2 = frem float %a2, %b2
+  %r3 = frem float %a3, %b3
+  store float %r0, ptr getelementptr inbounds (float, ptr @a, i64 0), align 8
+  store float %r1, ptr getelementptr inbounds (float, ptr @a, i64 1), align 8
+  store float %r2, ptr getelementptr inbounds (float, ptr @a, i64 2), align 8
+  store float %r3, ptr getelementptr inbounds (float, ptr @a, i64 3), align 8
+  ret void
+}
+