; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt < %s -interleaved-access -S | FileCheck %s --check-prefix=NEON
; RUN: opt < %s -interleaved-access -mtriple=aarch64-linux-gnu -mattr=+sve -force-streaming-compatible -S | FileCheck %s --check-prefix=SVE-FIXED
; RUN: opt < %s -passes=interleaved-access -S | FileCheck %s --check-prefix=NEON
; RUN: opt < %s -passes=interleaved-access -mtriple=aarch64-linux-gnu -mattr=+sve -force-streaming-compatible -S | FileCheck %s --check-prefix=SVE-FIXED
target triple = "aarch64-linux-gnu"
define void @deinterleave_i8_factor2(ptr %ptr) {
; NEON-LABEL: define void @deinterleave_i8_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <16 x i8>, <16 x i8> } @llvm.aarch64.neon.ld2.v16i8.p0(ptr [[PTR]])
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <16 x i8>, <16 x i8> } [[LDN]], 0
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <16 x i8>, <16 x i8> } [[LDN]], 1
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_i8_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0:[0-9]+]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <32 x i8>, ptr [[PTR]], align 1
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <16 x i8>, <16 x i8> } @llvm.vector.deinterleave2.v32i8(<32 x i8> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <16 x i8>, <16 x i8> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <16 x i8>, <16 x i8> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <32 x i8>, ptr %ptr, align 1
%deinterleave = tail call { <16 x i8>, <16 x i8> } @llvm.vector.deinterleave2.v32i8(<32 x i8> %load)
%extract1 = extractvalue { <16 x i8>, <16 x i8> } %deinterleave, 0
%extract2 = extractvalue { <16 x i8>, <16 x i8> } %deinterleave, 1
ret void
}
define void @deinterleave_i16_factor2(ptr %ptr) {
; NEON-LABEL: define void @deinterleave_i16_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <8 x i16>, <8 x i16> } @llvm.aarch64.neon.ld2.v8i16.p0(ptr [[PTR]])
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN]], 0
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN]], 1
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_i16_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <16 x i16>, ptr [[PTR]], align 2
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <8 x i16>, <8 x i16> } @llvm.vector.deinterleave2.v16i16(<16 x i16> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <16 x i16>, ptr %ptr, align 2
%deinterleave = tail call { <8 x i16>, <8 x i16> } @llvm.vector.deinterleave2.v16i16(<16 x i16> %load)
%extract1 = extractvalue { <8 x i16>, <8 x i16> } %deinterleave, 0
%extract2 = extractvalue { <8 x i16>, <8 x i16> } %deinterleave, 1
ret void
}
define void @deinterleave_8xi32_factor2(ptr %ptr) {
; NEON-LABEL: define void @deinterleave_8xi32_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0(ptr [[PTR]])
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 0
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[LDN]], 1
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_8xi32_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <8 x i32>, ptr [[PTR]], align 4
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <4 x i32>, <4 x i32> } @llvm.vector.deinterleave2.v8i32(<8 x i32> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <8 x i32>, ptr %ptr, align 4
%deinterleave = tail call { <4 x i32>, <4 x i32> } @llvm.vector.deinterleave2.v8i32(<8 x i32> %load)
%extract1 = extractvalue { <4 x i32>, <4 x i32> } %deinterleave, 0
%extract2 = extractvalue { <4 x i32>, <4 x i32> } %deinterleave, 1
ret void
}
define void @deinterleave_i64_factor2(ptr %ptr) {
; NEON-LABEL: define void @deinterleave_i64_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld2.v2i64.p0(ptr [[PTR]])
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[LDN]], 0
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[LDN]], 1
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_i64_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <4 x i64>, ptr [[PTR]], align 8
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <2 x i64>, <2 x i64> } @llvm.vector.deinterleave2.v4i64(<4 x i64> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <4 x i64>, ptr %ptr, align 8
%deinterleave = tail call { <2 x i64>, <2 x i64> } @llvm.vector.deinterleave2.v4i64(<4 x i64> %load)
%extract1 = extractvalue { <2 x i64>, <2 x i64> } %deinterleave, 0
%extract2 = extractvalue { <2 x i64>, <2 x i64> } %deinterleave, 1
ret void
}
define void @deinterleave_float_factor2(ptr %ptr) {
; NEON-LABEL: define void @deinterleave_float_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <4 x float>, <4 x float> } @llvm.aarch64.neon.ld2.v4f32.p0(ptr [[PTR]])
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <4 x float>, <4 x float> } [[LDN]], 0
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <4 x float>, <4 x float> } [[LDN]], 1
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_float_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <8 x float>, ptr [[PTR]], align 4
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <4 x float>, <4 x float> } @llvm.vector.deinterleave2.v8f32(<8 x float> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <4 x float>, <4 x float> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <4 x float>, <4 x float> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <8 x float>, ptr %ptr, align 4
%deinterleave = tail call { <4 x float>, <4 x float> } @llvm.vector.deinterleave2.v8f32(<8 x float> %load)
%extract1 = extractvalue { <4 x float>, <4 x float> } %deinterleave, 0
%extract2 = extractvalue { <4 x float>, <4 x float> } %deinterleave, 1
ret void
}
define void @deinterleave_double_factor2(ptr %ptr) {
; NEON-LABEL: define void @deinterleave_double_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <2 x double>, <2 x double> } @llvm.aarch64.neon.ld2.v2f64.p0(ptr [[PTR]])
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <2 x double>, <2 x double> } [[LDN]], 0
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <2 x double>, <2 x double> } [[LDN]], 1
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_double_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <4 x double>, ptr [[PTR]], align 8
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <2 x double>, <2 x double> } @llvm.vector.deinterleave2.v4f64(<4 x double> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <2 x double>, <2 x double> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <2 x double>, <2 x double> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <4 x double>, ptr %ptr, align 8
%deinterleave = tail call { <2 x double>, <2 x double> } @llvm.vector.deinterleave2.v4f64(<4 x double> %load)
%extract1 = extractvalue { <2 x double>, <2 x double> } %deinterleave, 0
%extract2 = extractvalue { <2 x double>, <2 x double> } %deinterleave, 1
ret void
}
define void @deinterleave_ptr_factor2(ptr %ptr) {
; NEON-LABEL: define void @deinterleave_ptr_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[LDN:%.*]] = call { <2 x ptr>, <2 x ptr> } @llvm.aarch64.neon.ld2.v2p0.p0(ptr [[PTR]])
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <2 x ptr>, <2 x ptr> } [[LDN]], 0
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <2 x ptr>, <2 x ptr> } [[LDN]], 1
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_ptr_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <4 x ptr>, ptr [[PTR]], align 8
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <2 x ptr>, <2 x ptr> } @llvm.vector.deinterleave2.v4p0(<4 x ptr> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <2 x ptr>, <2 x ptr> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <2 x ptr>, <2 x ptr> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <4 x ptr>, ptr %ptr, align 8
%deinterleave = tail call { <2 x ptr>, <2 x ptr> } @llvm.vector.deinterleave2.v4p0(<4 x ptr> %load)
%extract1 = extractvalue { <2 x ptr>, <2 x ptr> } %deinterleave, 0
%extract2 = extractvalue { <2 x ptr>, <2 x ptr> } %deinterleave, 1
ret void
}
define void @interleave_i8_factor2(ptr %ptr, <16 x i8> %l, <16 x i8> %r) {
; NEON-LABEL: define void @interleave_i8_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <16 x i8> [[L:%.*]], <16 x i8> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v16i8.p0(<16 x i8> [[L]], <16 x i8> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i8_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <16 x i8> [[L:%.*]], <16 x i8> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <32 x i8> @llvm.vector.interleave2.v32i8(<16 x i8> [[L]], <16 x i8> [[R]])
; SVE-FIXED-NEXT: store <32 x i8> [[INTERLEAVE]], ptr [[PTR]], align 1
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <32 x i8> @llvm.vector.interleave2.v32i8(<16 x i8> %l, <16 x i8> %r)
store <32 x i8> %interleave, ptr %ptr, align 1
ret void
}
define void @interleave_i16_factor2(ptr %ptr, <8 x i16> %l, <8 x i16> %r) {
; NEON-LABEL: define void @interleave_i16_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <8 x i16> [[L:%.*]], <8 x i16> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v8i16.p0(<8 x i16> [[L]], <8 x i16> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i16_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <8 x i16> [[L:%.*]], <8 x i16> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <16 x i16> @llvm.vector.interleave2.v16i16(<8 x i16> [[L]], <8 x i16> [[R]])
; SVE-FIXED-NEXT: store <16 x i16> [[INTERLEAVE]], ptr [[PTR]], align 2
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <16 x i16> @llvm.vector.interleave2.v16i16(<8 x i16> %l, <8 x i16> %r)
store <16 x i16> %interleave, ptr %ptr, align 2
ret void
}
define void @interleave_i32_factor2(ptr %ptr, <4 x i32> %l, <4 x i32> %r) {
; NEON-LABEL: define void @interleave_i32_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <4 x i32> [[L:%.*]], <4 x i32> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v4i32.p0(<4 x i32> [[L]], <4 x i32> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i32_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <4 x i32> [[L:%.*]], <4 x i32> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <8 x i32> @llvm.vector.interleave2.v8i32(<4 x i32> [[L]], <4 x i32> [[R]])
; SVE-FIXED-NEXT: store <8 x i32> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <8 x i32> @llvm.vector.interleave2.v8i32(<4 x i32> %l, <4 x i32> %r)
store <8 x i32> %interleave, ptr %ptr, align 4
ret void
}
define void @interleave_i64_factor2(ptr %ptr, <2 x i64> %l, <2 x i64> %r) {
; NEON-LABEL: define void @interleave_i64_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <2 x i64> [[L:%.*]], <2 x i64> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2i64.p0(<2 x i64> [[L]], <2 x i64> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_i64_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <2 x i64> [[L:%.*]], <2 x i64> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <4 x i64> @llvm.vector.interleave2.v4i64(<2 x i64> [[L]], <2 x i64> [[R]])
; SVE-FIXED-NEXT: store <4 x i64> [[INTERLEAVE]], ptr [[PTR]], align 8
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <4 x i64> @llvm.vector.interleave2.v4i64(<2 x i64> %l, <2 x i64> %r)
store <4 x i64> %interleave, ptr %ptr, align 8
ret void
}
define void @interleave_float_factor2(ptr %ptr, <4 x float> %l, <4 x float> %r) {
; NEON-LABEL: define void @interleave_float_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <4 x float> [[L:%.*]], <4 x float> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v4f32.p0(<4 x float> [[L]], <4 x float> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_float_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <4 x float> [[L:%.*]], <4 x float> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <8 x float> @llvm.vector.interleave2.v8f32(<4 x float> [[L]], <4 x float> [[R]])
; SVE-FIXED-NEXT: store <8 x float> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <8 x float> @llvm.vector.interleave2.v8f32(<4 x float> %l, <4 x float> %r)
store <8 x float> %interleave, ptr %ptr, align 4
ret void
}
define void @interleave_double_factor2(ptr %ptr, <2 x double> %l, <2 x double> %r) {
; NEON-LABEL: define void @interleave_double_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <2 x double> [[L:%.*]], <2 x double> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2f64.p0(<2 x double> [[L]], <2 x double> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_double_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <2 x double> [[L:%.*]], <2 x double> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <4 x double> @llvm.vector.interleave2.v4f64(<2 x double> [[L]], <2 x double> [[R]])
; SVE-FIXED-NEXT: store <4 x double> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <4 x double> @llvm.vector.interleave2.v4f64(<2 x double> %l, <2 x double> %r)
store <4 x double> %interleave, ptr %ptr, align 4
ret void
}
define void @interleave_ptr_factor2(ptr %ptr, <2 x ptr> %l, <2 x ptr> %r) {
; NEON-LABEL: define void @interleave_ptr_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <2 x ptr> [[L:%.*]], <2 x ptr> [[R:%.*]]) {
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[L]], <2 x ptr> [[R]], ptr [[PTR]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_ptr_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <2 x ptr> [[L:%.*]], <2 x ptr> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <4 x ptr> @llvm.vector.interleave2.v4p0(<2 x ptr> [[L]], <2 x ptr> [[R]])
; SVE-FIXED-NEXT: store <4 x ptr> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <4 x ptr> @llvm.vector.interleave2.v4p0(<2 x ptr> %l, <2 x ptr> %r)
store <4 x ptr> %interleave, ptr %ptr, align 4
ret void
}
define void @deinterleave_wide_i16_factor2(ptr %ptr) #0 {
; NEON-LABEL: define void @deinterleave_wide_i16_factor2
; NEON-SAME: (ptr [[PTR:%.*]]) {
; NEON-NEXT: [[TMP1:%.*]] = getelementptr <8 x i16>, ptr [[PTR]], i64 0
; NEON-NEXT: [[LDN:%.*]] = call { <8 x i16>, <8 x i16> } @llvm.aarch64.neon.ld2.v8i16.p0(ptr [[TMP1]])
; NEON-NEXT: [[TMP2:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN]], 0
; NEON-NEXT: [[TMP3:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> poison, <8 x i16> [[TMP2]], i64 0)
; NEON-NEXT: [[TMP4:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN]], 1
; NEON-NEXT: [[TMP5:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> poison, <8 x i16> [[TMP4]], i64 0)
; NEON-NEXT: [[TMP6:%.*]] = getelementptr <8 x i16>, ptr [[PTR]], i64 2
; NEON-NEXT: [[LDN1:%.*]] = call { <8 x i16>, <8 x i16> } @llvm.aarch64.neon.ld2.v8i16.p0(ptr [[TMP6]])
; NEON-NEXT: [[TMP7:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN1]], 0
; NEON-NEXT: [[TMP8:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> [[TMP3]], <8 x i16> [[TMP7]], i64 8)
; NEON-NEXT: [[TMP9:%.*]] = extractvalue { <8 x i16>, <8 x i16> } [[LDN1]], 1
; NEON-NEXT: [[TMP10:%.*]] = call <16 x i16> @llvm.vector.insert.v16i16.v8i16(<16 x i16> [[TMP5]], <8 x i16> [[TMP9]], i64 8)
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @deinterleave_wide_i16_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[LOAD:%.*]] = load <32 x i16>, ptr [[PTR]], align 2
; SVE-FIXED-NEXT: [[DEINTERLEAVE:%.*]] = tail call { <16 x i16>, <16 x i16> } @llvm.vector.deinterleave2.v32i16(<32 x i16> [[LOAD]])
; SVE-FIXED-NEXT: [[EXTRACT1:%.*]] = extractvalue { <16 x i16>, <16 x i16> } [[DEINTERLEAVE]], 0
; SVE-FIXED-NEXT: [[EXTRACT2:%.*]] = extractvalue { <16 x i16>, <16 x i16> } [[DEINTERLEAVE]], 1
; SVE-FIXED-NEXT: ret void
;
%load = load <32 x i16>, ptr %ptr, align 2
%deinterleave = tail call { <16 x i16>, <16 x i16> } @llvm.vector.deinterleave2.v32i16(<32 x i16> %load)
%extract1 = extractvalue { <16 x i16>, <16 x i16> } %deinterleave, 0
%extract2 = extractvalue { <16 x i16>, <16 x i16> } %deinterleave, 1
ret void
}
define void @interleave_wide_ptr_factor2(ptr %ptr, <8 x ptr> %l, <8 x ptr> %r) {
; NEON-LABEL: define void @interleave_wide_ptr_factor2
; NEON-SAME: (ptr [[PTR:%.*]], <8 x ptr> [[L:%.*]], <8 x ptr> [[R:%.*]]) {
; NEON-NEXT: [[TMP1:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 0
; NEON-NEXT: [[TMP2:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 0)
; NEON-NEXT: [[TMP3:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 0)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP2]], <2 x ptr> [[TMP3]], ptr [[TMP1]])
; NEON-NEXT: [[TMP4:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 2
; NEON-NEXT: [[TMP5:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 2)
; NEON-NEXT: [[TMP6:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 2)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP5]], <2 x ptr> [[TMP6]], ptr [[TMP4]])
; NEON-NEXT: [[TMP7:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 4
; NEON-NEXT: [[TMP8:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 4)
; NEON-NEXT: [[TMP9:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 4)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP8]], <2 x ptr> [[TMP9]], ptr [[TMP7]])
; NEON-NEXT: [[TMP10:%.*]] = getelementptr <2 x ptr>, ptr [[PTR]], i64 6
; NEON-NEXT: [[TMP11:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[L]], i64 6)
; NEON-NEXT: [[TMP12:%.*]] = call <2 x ptr> @llvm.vector.extract.v2p0.v8p0(<8 x ptr> [[R]], i64 6)
; NEON-NEXT: call void @llvm.aarch64.neon.st2.v2p0.p0(<2 x ptr> [[TMP11]], <2 x ptr> [[TMP12]], ptr [[TMP10]])
; NEON-NEXT: ret void
;
; SVE-FIXED-LABEL: define void @interleave_wide_ptr_factor2
; SVE-FIXED-SAME: (ptr [[PTR:%.*]], <8 x ptr> [[L:%.*]], <8 x ptr> [[R:%.*]]) #[[ATTR0]] {
; SVE-FIXED-NEXT: [[INTERLEAVE:%.*]] = tail call <16 x ptr> @llvm.vector.interleave2.v16p0(<8 x ptr> [[L]], <8 x ptr> [[R]])
; SVE-FIXED-NEXT: store <16 x ptr> [[INTERLEAVE]], ptr [[PTR]], align 4
; SVE-FIXED-NEXT: ret void
;
%interleave = tail call <16 x ptr> @llvm.vector.interleave2.v16p0(<8 x ptr> %l, <8 x ptr> %r)
store <16 x ptr> %interleave, ptr %ptr, align 4
ret void
}
declare { <16 x i8>, <16 x i8> } @llvm.vector.deinterleave2.v32i8(<32 x i8>)
declare { <8 x i16>, <8 x i16> } @llvm.vector.deinterleave2.v16i16(<16 x i16>)
declare { <4 x i32>, <4 x i32> } @llvm.vector.deinterleave2.v8i32(<8 x i32>)
declare { <2 x i64>, <2 x i64> } @llvm.vector.deinterleave2.v4i64(<4 x i64>)
declare { <4 x float>, <4 x float> } @llvm.vector.deinterleave2.v8f32(<8 x float>)
declare { <2 x double>, <2 x double> } @llvm.vector.deinterleave2.v4f64(<4 x double>)
declare { <2 x ptr>, <2 x ptr> } @llvm.vector.deinterleave2.v4p0(<4 x ptr>)
declare { <16 x i16>, <16 x i16> } @llvm.vector.deinterleave2.v32i16(<32 x i16>)
declare <32 x i8> @llvm.vector.interleave2.v32i8(<16 x i8>, <16 x i8>)
declare <16 x i16> @llvm.vector.interleave2.v16i16(<8 x i16>, <8 x i16>)
declare <8 x i32> @llvm.vector.interleave2.v8i32(<4 x i32>, <4 x i32>)
declare <4 x i64> @llvm.vector.interleave2.v4i64(<2 x i64>, <2 x i64>)
declare <8 x float> @llvm.vector.interleave2.v8f32(<4 x float>, <4 x float>)
declare <4 x double> @llvm.vector.interleave2.v4f64(<2 x double>, <2 x double>)
declare <4 x ptr> @llvm.vector.interleave2.v4p0(<2 x ptr>, <2 x ptr>)
declare <16 x ptr> @llvm.vector.interleave2.v16p0(<8 x ptr>, <8 x ptr>)