irtranslator-reductions.ll | Explore in Territory

; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -O0 -mtriple=aarch64-apple-ios -global-isel -disable-expand-reductions -stop-after=irtranslator %s -o - | FileCheck %s

declare float @llvm.vector.reduce.fadd.v4f32(float, <4 x float>)
declare double @llvm.vector.reduce.fmul.v4f64(double, <4 x double>)

define float @fadd_seq(float %start, <4 x float> %vec) {
  ; CHECK-LABEL: name: fadd_seq
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q1, $s0
  ; CHECK:   [[COPY:%[0-9]+]]:_(s32) = COPY $s0
  ; CHECK:   [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $q1
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY1]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_SEQ_FADD:%[0-9]+]]:_(s32) = G_VECREDUCE_SEQ_FADD [[COPY]](s32), [[BITCAST]](<4 x s32>)
  ; CHECK:   $s0 = COPY [[VECREDUCE_SEQ_FADD]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call float @llvm.vector.reduce.fadd.v4f32(float %start, <4 x float> %vec)
  ret float %res
}

define float @fadd_fast(float %start, <4 x float> %vec) {
  ; CHECK-LABEL: name: fadd_fast
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q1, $s0
  ; CHECK:   [[COPY:%[0-9]+]]:_(s32) = COPY $s0
  ; CHECK:   [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $q1
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY1]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FADD:%[0-9]+]]:_(s32) = reassoc G_VECREDUCE_FADD [[BITCAST]](<4 x s32>)
  ; CHECK:   [[FADD:%[0-9]+]]:_(s32) = reassoc G_FADD [[COPY]], [[VECREDUCE_FADD]]
  ; CHECK:   $s0 = COPY [[FADD]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call reassoc float @llvm.vector.reduce.fadd.v4f32(float %start, <4 x float> %vec)
  ret float %res
}

define double @fmul_seq(double %start, <4 x double> %vec) {
  ; CHECK-LABEL: name: fmul_seq
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $d0, $q1, $q2
  ; CHECK:   [[COPY:%[0-9]+]]:_(s64) = COPY $d0
  ; CHECK:   [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $q1
  ; CHECK:   [[COPY2:%[0-9]+]]:_(<2 x s64>) = COPY $q2
  ; CHECK:   [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[COPY1]](<2 x s64>), [[COPY2]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_SEQ_FMUL:%[0-9]+]]:_(s64) = G_VECREDUCE_SEQ_FMUL [[COPY]](s64), [[CONCAT_VECTORS]](<4 x s64>)
  ; CHECK:   $d0 = COPY [[VECREDUCE_SEQ_FMUL]](s64)
  ; CHECK:   RET_ReallyLR implicit $d0
  %res = call double @llvm.vector.reduce.fmul.v4f64(double %start, <4 x double> %vec)
  ret double %res
}

define double @fmul_fast(double %start, <4 x double> %vec) {
  ; CHECK-LABEL: name: fmul_fast
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $d0, $q1, $q2
  ; CHECK:   [[COPY:%[0-9]+]]:_(s64) = COPY $d0
  ; CHECK:   [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $q1
  ; CHECK:   [[COPY2:%[0-9]+]]:_(<2 x s64>) = COPY $q2
  ; CHECK:   [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[COPY1]](<2 x s64>), [[COPY2]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FMUL:%[0-9]+]]:_(s64) = reassoc G_VECREDUCE_FMUL [[CONCAT_VECTORS]](<4 x s64>)
  ; CHECK:   [[FMUL:%[0-9]+]]:_(s64) = reassoc G_FMUL [[COPY]], [[VECREDUCE_FMUL]]
  ; CHECK:   $d0 = COPY [[FMUL]](s64)
  ; CHECK:   RET_ReallyLR implicit $d0
  %res = call reassoc double @llvm.vector.reduce.fmul.v4f64(double %start, <4 x double> %vec)
  ret double %res
}

declare float @llvm.vector.reduce.fmax.v4f32(<4 x float>)
declare float @llvm.vector.reduce.fmin.v4f32(<4 x float>)
declare float @llvm.vector.reduce.fmaximum.v4f32(<4 x float>)
declare float @llvm.vector.reduce.fminimum.v4f32(<4 x float>)

define float @fmax(<4 x float> %vec) {
  ; CHECK-LABEL: name: fmax
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FMAX:%[0-9]+]]:_(s32) = G_VECREDUCE_FMAX [[BITCAST]](<4 x s32>)
  ; CHECK:   $s0 = COPY [[VECREDUCE_FMAX]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call float @llvm.vector.reduce.fmax.v4f32(<4 x float> %vec)
  ret float %res
}

define float @fmin(<4 x float> %vec) {
  ; CHECK-LABEL: name: fmin
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FMIN:%[0-9]+]]:_(s32) = G_VECREDUCE_FMIN [[BITCAST]](<4 x s32>)
  ; CHECK:   $s0 = COPY [[VECREDUCE_FMIN]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call float @llvm.vector.reduce.fmin.v4f32(<4 x float> %vec)
  ret float %res
}

define float @fmin_nnan(<4 x float> %vec) {
  ; CHECK-LABEL: name: fmin_nnan
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FMIN:%[0-9]+]]:_(s32) = nnan G_VECREDUCE_FMIN [[BITCAST]](<4 x s32>)
  ; CHECK:   $s0 = COPY [[VECREDUCE_FMIN]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call nnan float @llvm.vector.reduce.fmin.v4f32(<4 x float> %vec)
  ret float %res
}

define float @fmaximum(<4 x float> %vec) {
  ; CHECK-LABEL: name: fmaximum
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FMAX:%[0-9]+]]:_(s32) = G_VECREDUCE_FMAXIMUM [[BITCAST]](<4 x s32>)
  ; CHECK:   $s0 = COPY [[VECREDUCE_FMAX]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call float @llvm.vector.reduce.fmaximum.v4f32(<4 x float> %vec)
  ret float %res
}

define float @fminimum(<4 x float> %vec) {
  ; CHECK-LABEL: name: fminimum
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FMIN:%[0-9]+]]:_(s32) = G_VECREDUCE_FMINIMUM [[BITCAST]](<4 x s32>)
  ; CHECK:   $s0 = COPY [[VECREDUCE_FMIN]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call float @llvm.vector.reduce.fminimum.v4f32(<4 x float> %vec)
  ret float %res
}

define float @fminimum_nnan(<4 x float> %vec) {
  ; CHECK-LABEL: name: fminimum_nnan
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
  ; CHECK:   [[BITCAST:%[0-9]+]]:_(<4 x s32>) = G_BITCAST [[COPY]](<2 x s64>)
  ; CHECK:   [[VECREDUCE_FMIN:%[0-9]+]]:_(s32) = nnan G_VECREDUCE_FMINIMUM [[BITCAST]](<4 x s32>)
  ; CHECK:   $s0 = COPY [[VECREDUCE_FMIN]](s32)
  ; CHECK:   RET_ReallyLR implicit $s0
  %res = call nnan float @llvm.vector.reduce.fminimum.v4f32(<4 x float> %vec)
  ret float %res
}

declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>)

define i32 @add(<4 x i32> %vec) {
  ; CHECK-LABEL: name: add
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_ADD:%[0-9]+]]:_(s32) = G_VECREDUCE_ADD [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_ADD]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %vec)
  ret i32 %res
}

declare i32 @llvm.vector.reduce.mul.v4i32(<4 x i32>)

define i32 @mul(<4 x i32> %vec) {
  ; CHECK-LABEL: name: mul
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_MUL:%[0-9]+]]:_(s32) = G_VECREDUCE_MUL [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_MUL]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> %vec)
  ret i32 %res
}

declare i32 @llvm.vector.reduce.and.v4i32(<4 x i32>)

define i32 @and(<4 x i32> %vec) {
  ; CHECK-LABEL: name: and
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_AND:%[0-9]+]]:_(s32) = G_VECREDUCE_AND [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_AND]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> %vec)
  ret i32 %res
}

declare i32 @llvm.vector.reduce.or.v4i32(<4 x i32>)

define i32 @or(<4 x i32> %vec) {
  ; CHECK-LABEL: name: or
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_OR:%[0-9]+]]:_(s32) = G_VECREDUCE_OR [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_OR]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> %vec)
  ret i32 %res
}

declare i32 @llvm.vector.reduce.xor.v4i32(<4 x i32>)

define i32 @xor(<4 x i32> %vec) {
  ; CHECK-LABEL: name: xor
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_XOR:%[0-9]+]]:_(s32) = G_VECREDUCE_XOR [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_XOR]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> %vec)
  ret i32 %res
}

declare i32 @llvm.vector.reduce.smax.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.smin.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.umax.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.umin.v4i32(<4 x i32>)

define i32 @smax(<4 x i32> %vec) {
  ; CHECK-LABEL: name: smax
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_SMAX:%[0-9]+]]:_(s32) = G_VECREDUCE_SMAX [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_SMAX]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %vec)
  ret i32 %res
}

define i32 @smin(<4 x i32> %vec) {
  ; CHECK-LABEL: name: smin
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_SMIN:%[0-9]+]]:_(s32) = G_VECREDUCE_SMIN [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_SMIN]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %vec)
  ret i32 %res
}

define i32 @umax(<4 x i32> %vec) {
  ; CHECK-LABEL: name: umax
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_UMAX:%[0-9]+]]:_(s32) = G_VECREDUCE_UMAX [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_UMAX]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %vec)
  ret i32 %res
}

define i32 @umin(<4 x i32> %vec) {
  ; CHECK-LABEL: name: umin
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK:   liveins: $q0
  ; CHECK:   [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
  ; CHECK:   [[VECREDUCE_UMIN:%[0-9]+]]:_(s32) = G_VECREDUCE_UMIN [[COPY]](<4 x s32>)
  ; CHECK:   $w0 = COPY [[VECREDUCE_UMIN]](s32)
  ; CHECK:   RET_ReallyLR implicit $w0
  %res = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %vec)
  ret i32 %res
}
llvm/llvm/test/CodeGen/AArch64/GlobalISel/irtranslator-reductions.ll
