llvm/llvm/test/CodeGen/AArch64/fold-csel-cttz-and.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 < %s | FileCheck %s

;; Check the transformation
;; CSEL 0, cttz, cc -> AND cttz numbits-1
;; for cttz in the case of i32 and i64 respectively

;; Cases for which the optimzation takes place
define i32 @cttzi32(i32 %x) {
; CHECK-LABEL: cttzi32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit w8, w0
; CHECK-NEXT:    clz w8, w8
; CHECK-NEXT:    and w0, w8, #0x1f
; CHECK-NEXT:    ret
entry:
  %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
  %1 = icmp eq i32 %x, 0
  %2 = select i1 %1, i32 0, i32 %0
  ret i32 %2
}

define i64 @cttzi64(i64 %x) {
; CHECK-LABEL: cttzi64:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit x8, x0
; CHECK-NEXT:    clz x8, x8
; CHECK-NEXT:    and x0, x8, #0x3f
; CHECK-NEXT:    ret
entry:
  %0 = call i64 @llvm.cttz.i64(i64 %x, i1 true)
  %1 = icmp eq i64 %x, 0
  %2 = select i1 %1, i64 0, i64 %0
  ret i64 %2
}

define i32 @cttzi32ne(i32 %x) {
; CHECK-LABEL: cttzi32ne:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit w8, w0
; CHECK-NEXT:    clz w8, w8
; CHECK-NEXT:    and w0, w8, #0x1f
; CHECK-NEXT:    ret
entry:
  %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
  %1 = icmp ne i32 %x, 0
  %2 = select i1 %1, i32 %0, i32 0
  ret i32 %2
}

define i64 @cttzi64ne(i64 %x) {
; CHECK-LABEL: cttzi64ne:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit x8, x0
; CHECK-NEXT:    clz x8, x8
; CHECK-NEXT:    and x0, x8, #0x3f
; CHECK-NEXT:    ret
entry:
  %0 = call i64 @llvm.cttz.i64(i64 %x, i1 true)
  %1 = icmp ne i64 %x, 0
  %2 = select i1 %1, i64 %0, i64 0
  ret i64 %2
}

define i32 @cttztrunc(i64 %x) {
; CHECK-LABEL: cttztrunc:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit x8, x0
; CHECK-NEXT:    clz x8, x8
; CHECK-NEXT:    and w0, w8, #0x3f
; CHECK-NEXT:    ret
entry:
  %0 = call i64 @llvm.cttz.i64(i64 %x, i1 true)
  %1 = icmp eq i64 %x, 0
  %2 = select i1 %1, i64 0, i64 %0
  %3 = trunc i64 %2 to i32
  ret i32 %3
}

;; Cases for which the optimization does not take place
define i32 @cttzne(i32 %x) {
; CHECK-LABEL: cttzne:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit w8, w0
; CHECK-NEXT:    cmp w0, #0
; CHECK-NEXT:    clz w8, w8
; CHECK-NEXT:    csel w0, wzr, w8, ne
; CHECK-NEXT:    ret
entry:
  %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
  %1 = icmp ne i32 %x, 0
  %2 = select i1 %1, i32 0, i32 %0
  ret i32 %2
}

define i32 @cttzxnot0(i32 %x) {
; CHECK-LABEL: cttzxnot0:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit w8, w0
; CHECK-NEXT:    cmp w0, #10
; CHECK-NEXT:    clz w8, w8
; CHECK-NEXT:    csel w0, wzr, w8, eq
; CHECK-NEXT:    ret
entry:
  %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
  %1 = icmp eq i32 %x, 10
  %2 = select i1 %1, i32 0, i32 %0
  ret i32 %2
}

define i32 @cttzlhsnot0(i32 %x) {
; CHECK-LABEL: cttzlhsnot0:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit w9, w0
; CHECK-NEXT:    mov w8, #10 // =0xa
; CHECK-NEXT:    cmp w0, #0
; CHECK-NEXT:    clz w9, w9
; CHECK-NEXT:    csel w0, w8, w9, eq
; CHECK-NEXT:    ret
entry:
  %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
  %1 = icmp eq i32 %x, 0
  %2 = select i1 %1, i32 10, i32 %0
  ret i32 %2
}

define i32 @notcttz(i32 %x) {
; CHECK-LABEL: notcttz:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    clz w8, w0
; CHECK-NEXT:    cmp w0, #0
; CHECK-NEXT:    csel w0, wzr, w8, eq
; CHECK-NEXT:    ret
entry:
  %0 = call i32 @llvm.ctlz.i32(i32 %x, i1 true)
  %1 = icmp eq i32 %x, 0
  %2 = select i1 %1, i32 0, i32 %0
  ret i32 %2
}

define i32 @cttzlhsnotx(i32 %x, i32 %y) {
; CHECK-LABEL: cttzlhsnotx:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    rbit w8, w0
; CHECK-NEXT:    cmp w1, #0
; CHECK-NEXT:    clz w8, w8
; CHECK-NEXT:    csel w0, wzr, w8, eq
; CHECK-NEXT:    ret
entry:
  %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
  %1 = icmp eq i32 %y, 0
  %2 = select i1 %1, i32 0, i32 %0
  ret i32 %2
}

declare i32 @llvm.cttz.i32(i32, i1)

declare i64 @llvm.cttz.i64(i64, i1)

declare i32 @llvm.ctlz.i32(i32, i1)