blob: c7a89612d278f20ca06a238b682548b6c030d412 [file] [log] [blame]
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mattr=+sve -force-streaming-compatible-sve < %s | FileCheck %s --check-prefixes=CHECK,SVE
; RUN: llc -mattr=+sve2 -force-streaming-compatible-sve < %s | FileCheck %s --check-prefixes=CHECK,SVE2
; RUN: llc -mattr=+sme -force-streaming-compatible-sve < %s | FileCheck %s --check-prefixes=CHECK,SVE2
target triple = "aarch64-unknown-linux-gnu"
;
; sext i1 -> i32
;
; NOTE: Covers the scenario where a SIGN_EXTEND_INREG is required, whose inreg
; type's element type is not byte based and thus cannot be lowered directly to
; an SVE instruction.
define void @sext_v8i1_v8i32(<8 x i1> %a, ptr %out) {
; CHECK-LABEL: sext_v8i1_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: uunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: lsl z1.s, z1.s, #31
; CHECK-NEXT: lsl z0.s, z0.s, #31
; CHECK-NEXT: asr z1.s, z1.s, #31
; CHECK-NEXT: asr z0.s, z0.s, #31
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <8 x i1> %a to <8 x i32>
store <8 x i32> %b, ptr %out
ret void
}
;
; sext i3 -> i64
;
; NOTE: Covers the scenario where a SIGN_EXTEND_INREG is required, whose inreg
; type's element type is not power-of-2 based and thus cannot be lowered
; directly to an SVE instruction.
define void @sext_v4i3_v4i64(<4 x i3> %a, ptr %out) {
; CHECK-LABEL: sext_v4i3_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z1.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: lsl z1.d, z1.d, #61
; CHECK-NEXT: lsl z0.d, z0.d, #61
; CHECK-NEXT: asr z1.d, z1.d, #61
; CHECK-NEXT: asr z0.d, z0.d, #61
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <4 x i3> %a to <4 x i64>
store <4 x i64> %b, ptr %out
ret void
}
;
; sext i8 -> i16
;
define void @sext_v16i8_v16i16(<16 x i8> %a, ptr %out) {
; CHECK-LABEL: sext_v16i8_v16i16:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: sunpklo z1.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <16 x i8> %a to <16 x i16>
store <16 x i16>%b, ptr %out
ret void
}
; NOTE: Extra 'add' is to prevent the extend being combined with the load.
define void @sext_v32i8_v32i16(ptr %in, ptr %out) {
; CHECK-LABEL: sext_v32i8_v32i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.b, z0.b, z0.b
; CHECK-NEXT: add z1.b, z1.b, z1.b
; CHECK-NEXT: sunpklo z2.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z3.h, z1.b
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: sunpklo z1.h, z1.b
; CHECK-NEXT: stp q2, q0, [x1, #32]
; CHECK-NEXT: stp q3, q1, [x1]
; CHECK-NEXT: ret
%a = load <32 x i8>, ptr %in
%b = add <32 x i8> %a, %a
%c = sext <32 x i8> %b to <32 x i16>
store <32 x i16> %c, ptr %out
ret void
}
;
; sext i8 -> i32
;
define void @sext_v8i8_v8i32(<8 x i8> %a, ptr %out) {
; CHECK-LABEL: sext_v8i8_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: sunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <8 x i8> %a to <8 x i32>
store <8 x i32>%b, ptr %out
ret void
}
define void @sext_v16i8_v16i32(<16 x i8> %a, ptr %out) {
; CHECK-LABEL: sext_v16i8_v16i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: sunpklo z1.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: sunpklo z2.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z1.s, z1.h
; CHECK-NEXT: sunpklo z3.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: stp q2, q1, [x0]
; CHECK-NEXT: stp q3, q0, [x0, #32]
; CHECK-NEXT: ret
%b = sext <16 x i8> %a to <16 x i32>
store <16 x i32> %b, ptr %out
ret void
}
define void @sext_v32i8_v32i32(ptr %in, ptr %out) {
; CHECK-LABEL: sext_v32i8_v32i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.b, z0.b, z0.b
; CHECK-NEXT: add z1.b, z1.b, z1.b
; CHECK-NEXT: sunpklo z2.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z3.h, z1.b
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: sunpklo z1.h, z1.b
; CHECK-NEXT: sunpklo z4.s, z2.h
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: sunpklo z5.s, z3.h
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: sunpklo z6.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z2.s, z2.h
; CHECK-NEXT: sunpklo z7.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z3.s, z3.h
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: sunpklo z1.s, z1.h
; CHECK-NEXT: stp q4, q2, [x1, #64]
; CHECK-NEXT: stp q5, q3, [x1]
; CHECK-NEXT: stp q6, q0, [x1, #96]
; CHECK-NEXT: stp q7, q1, [x1, #32]
; CHECK-NEXT: ret
%a = load <32 x i8>, ptr %in
%b = add <32 x i8> %a, %a
%c = sext <32 x i8> %b to <32 x i32>
store <32 x i32> %c, ptr %out
ret void
}
;
; sext i8 -> i64
;
; NOTE: v4i8 is an unpacked typed stored within a v4i16 container. The sign
; extend is a two step process where the container is any_extend'd with the
; result feeding an inreg sign extend.
define void @sext_v4i8_v4i64(<4 x i8> %a, ptr %out) {
; CHECK-LABEL: sext_v4i8_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: ptrue p0.d, vl2
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z1.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: sxtb z1.d, p0/m, z1.d
; CHECK-NEXT: sxtb z0.d, p0/m, z0.d
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <4 x i8> %a to <4 x i64>
store <4 x i64>%b, ptr %out
ret void
}
define void @sext_v8i8_v8i64(<8 x i8> %a, ptr %out) {
; CHECK-LABEL: sext_v8i8_v8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: sunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: sunpklo z2.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z3.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z1.d, z1.s
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: stp q2, q1, [x0]
; CHECK-NEXT: stp q3, q0, [x0, #32]
; CHECK-NEXT: ret
%b = sext <8 x i8> %a to <8 x i64>
store <8 x i64>%b, ptr %out
ret void
}
define void @sext_v16i8_v16i64(<16 x i8> %a, ptr %out) {
; CHECK-LABEL: sext_v16i8_v16i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: sunpklo z1.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: sunpklo z2.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z1.s, z1.h
; CHECK-NEXT: sunpklo z3.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z4.d, z2.s
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: mov z7.d, z1.d
; CHECK-NEXT: sunpklo z2.d, z2.s
; CHECK-NEXT: sunpklo z5.d, z3.s
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: ext z7.b, z7.b, z1.b, #8
; CHECK-NEXT: sunpklo z1.d, z1.s
; CHECK-NEXT: mov z6.d, z0.d
; CHECK-NEXT: sunpklo z3.d, z3.s
; CHECK-NEXT: stp q4, q2, [x0]
; CHECK-NEXT: sunpklo z4.d, z7.s
; CHECK-NEXT: ext z6.b, z6.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: stp q5, q3, [x0, #64]
; CHECK-NEXT: sunpklo z2.d, z6.s
; CHECK-NEXT: stp q1, q4, [x0, #32]
; CHECK-NEXT: stp q0, q2, [x0, #96]
; CHECK-NEXT: ret
%b = sext <16 x i8> %a to <16 x i64>
store <16 x i64> %b, ptr %out
ret void
}
define void @sext_v32i8_v32i64(ptr %in, ptr %out) {
; CHECK-LABEL: sext_v32i8_v32i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.b, z0.b, z0.b
; CHECK-NEXT: add z1.b, z1.b, z1.b
; CHECK-NEXT: mov z2.d, z0.d
; CHECK-NEXT: sunpklo z0.h, z0.b
; CHECK-NEXT: mov z3.d, z1.d
; CHECK-NEXT: sunpklo z1.h, z1.b
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: sunpklo z4.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z5.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z2.h, z2.b
; CHECK-NEXT: sunpklo z3.h, z3.b
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: sunpklo z16.d, z4.s
; CHECK-NEXT: ext z4.b, z4.b, z4.b, #8
; CHECK-NEXT: sunpklo z1.s, z1.h
; CHECK-NEXT: sunpklo z17.d, z5.s
; CHECK-NEXT: ext z5.b, z5.b, z5.b, #8
; CHECK-NEXT: sunpklo z6.s, z2.h
; CHECK-NEXT: sunpklo z7.s, z3.h
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: sunpklo z4.d, z4.s
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: sunpklo z19.d, z0.s
; CHECK-NEXT: sunpklo z5.d, z5.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z2.s, z2.h
; CHECK-NEXT: sunpklo z18.d, z6.s
; CHECK-NEXT: ext z6.b, z6.b, z6.b, #8
; CHECK-NEXT: sunpklo z3.s, z3.h
; CHECK-NEXT: stp q16, q4, [x1, #128]
; CHECK-NEXT: mov z16.d, z7.d
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: stp q17, q5, [x1]
; CHECK-NEXT: sunpklo z5.d, z7.s
; CHECK-NEXT: sunpklo z4.d, z6.s
; CHECK-NEXT: mov z6.d, z1.d
; CHECK-NEXT: ext z16.b, z16.b, z7.b, #8
; CHECK-NEXT: mov z7.d, z2.d
; CHECK-NEXT: stp q19, q0, [x1, #160]
; CHECK-NEXT: sunpklo z0.d, z2.s
; CHECK-NEXT: ext z6.b, z6.b, z1.b, #8
; CHECK-NEXT: sunpklo z1.d, z1.s
; CHECK-NEXT: stp q18, q4, [x1, #192]
; CHECK-NEXT: mov z4.d, z3.d
; CHECK-NEXT: ext z7.b, z7.b, z2.b, #8
; CHECK-NEXT: sunpklo z16.d, z16.s
; CHECK-NEXT: sunpklo z6.d, z6.s
; CHECK-NEXT: ext z4.b, z4.b, z3.b, #8
; CHECK-NEXT: sunpklo z2.d, z7.s
; CHECK-NEXT: sunpklo z3.d, z3.s
; CHECK-NEXT: stp q5, q16, [x1, #64]
; CHECK-NEXT: stp q1, q6, [x1, #32]
; CHECK-NEXT: sunpklo z1.d, z4.s
; CHECK-NEXT: stp q0, q2, [x1, #224]
; CHECK-NEXT: stp q3, q1, [x1, #96]
; CHECK-NEXT: ret
%a = load <32 x i8>, ptr %in
%b = add <32 x i8> %a, %a
%c = sext <32 x i8> %b to <32 x i64>
store <32 x i64> %c, ptr %out
ret void
}
;
; sext i16 -> i32
;
define void @sext_v8i16_v8i32(<8 x i16> %a, ptr %out) {
; CHECK-LABEL: sext_v8i16_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: sunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <8 x i16> %a to <8 x i32>
store <8 x i32>%b, ptr %out
ret void
}
define void @sext_v16i16_v16i32(ptr %in, ptr %out) {
; CHECK-LABEL: sext_v16i16_v16i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.h, z0.h, z0.h
; CHECK-NEXT: add z1.h, z1.h, z1.h
; CHECK-NEXT: sunpklo z2.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z3.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: sunpklo z1.s, z1.h
; CHECK-NEXT: stp q2, q0, [x1, #32]
; CHECK-NEXT: stp q3, q1, [x1]
; CHECK-NEXT: ret
%a = load <16 x i16>, ptr %in
%b = add <16 x i16> %a, %a
%c = sext <16 x i16> %b to <16 x i32>
store <16 x i32> %c, ptr %out
ret void
}
;
; sext i16 -> i64
;
define void @sext_v4i16_v4i64(<4 x i16> %a, ptr %out) {
; CHECK-LABEL: sext_v4i16_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: sunpklo z1.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <4 x i16> %a to <4 x i64>
store <4 x i64>%b, ptr %out
ret void
}
define void @sext_v8i16_v8i64(<8 x i16> %a, ptr %out) {
; CHECK-LABEL: sext_v8i16_v8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: sunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: sunpklo z2.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z1.d, z1.s
; CHECK-NEXT: sunpklo z3.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: stp q2, q1, [x0]
; CHECK-NEXT: stp q3, q0, [x0, #32]
; CHECK-NEXT: ret
%b = sext <8 x i16> %a to <8 x i64>
store <8 x i64>%b, ptr %out
ret void
}
define void @sext_v16i16_v16i64(ptr %in, ptr %out) {
; CHECK-LABEL: sext_v16i16_v16i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.h, z0.h, z0.h
; CHECK-NEXT: add z1.h, z1.h, z1.h
; CHECK-NEXT: sunpklo z2.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z3.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z0.s, z0.h
; CHECK-NEXT: sunpklo z1.s, z1.h
; CHECK-NEXT: sunpklo z4.d, z2.s
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: sunpklo z5.d, z3.s
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: sunpklo z6.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z2.d, z2.s
; CHECK-NEXT: sunpklo z7.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z3.d, z3.s
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: sunpklo z1.d, z1.s
; CHECK-NEXT: stp q4, q2, [x1, #64]
; CHECK-NEXT: stp q5, q3, [x1]
; CHECK-NEXT: stp q6, q0, [x1, #96]
; CHECK-NEXT: stp q7, q1, [x1, #32]
; CHECK-NEXT: ret
%a = load <16 x i16>, ptr %in
%b = add <16 x i16> %a, %a
%c = sext <16 x i16> %b to <16 x i64>
store <16 x i64> %c, ptr %out
ret void
}
;
; sext i32 -> i64
;
define void @sext_v4i32_v4i64(<4 x i32> %a, ptr %out) {
; CHECK-LABEL: sext_v4i32_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: sunpklo z1.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = sext <4 x i32> %a to <4 x i64>
store <4 x i64>%b, ptr %out
ret void
}
define void @sext_v8i32_v8i64(ptr %in, ptr %out) {
; CHECK-LABEL: sext_v8i32_v8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.s, z0.s, z0.s
; CHECK-NEXT: add z1.s, z1.s, z1.s
; CHECK-NEXT: sunpklo z2.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: sunpklo z3.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: sunpklo z0.d, z0.s
; CHECK-NEXT: sunpklo z1.d, z1.s
; CHECK-NEXT: stp q2, q0, [x1, #32]
; CHECK-NEXT: stp q3, q1, [x1]
; CHECK-NEXT: ret
%a = load <8 x i32>, ptr %in
%b = add <8 x i32> %a, %a
%c = sext <8 x i32> %b to <8 x i64>
store <8 x i64> %c, ptr %out
ret void
}
;
; zext i8 -> i16
;
define void @zext_v16i8_v16i16(<16 x i8> %a, ptr %out) {
; CHECK-LABEL: zext_v16i8_v16i16:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: uunpklo z1.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = zext <16 x i8> %a to <16 x i16>
store <16 x i16>%b, ptr %out
ret void
}
; NOTE: Extra 'add' is to prevent the extend being combined with the load.
define void @zext_v32i8_v32i16(ptr %in, ptr %out) {
; CHECK-LABEL: zext_v32i8_v32i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.b, z0.b, z0.b
; CHECK-NEXT: add z1.b, z1.b, z1.b
; CHECK-NEXT: uunpklo z2.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z3.h, z1.b
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: uunpklo z1.h, z1.b
; CHECK-NEXT: stp q2, q0, [x1, #32]
; CHECK-NEXT: stp q3, q1, [x1]
; CHECK-NEXT: ret
%a = load <32 x i8>, ptr %in
%b = add <32 x i8> %a, %a
%c = zext <32 x i8> %b to <32 x i16>
store <32 x i16> %c, ptr %out
ret void
}
;
; zext i8 -> i32
;
define void @zext_v8i8_v8i32(<8 x i8> %a, ptr %out) {
; CHECK-LABEL: zext_v8i8_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: uunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = zext <8 x i8> %a to <8 x i32>
store <8 x i32>%b, ptr %out
ret void
}
define void @zext_v16i8_v16i32(<16 x i8> %a, ptr %out) {
; CHECK-LABEL: zext_v16i8_v16i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: uunpklo z1.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: uunpklo z2.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z1.s, z1.h
; CHECK-NEXT: uunpklo z3.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: stp q2, q1, [x0]
; CHECK-NEXT: stp q3, q0, [x0, #32]
; CHECK-NEXT: ret
%b = zext <16 x i8> %a to <16 x i32>
store <16 x i32> %b, ptr %out
ret void
}
define void @zext_v32i8_v32i32(ptr %in, ptr %out) {
; CHECK-LABEL: zext_v32i8_v32i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.b, z0.b, z0.b
; CHECK-NEXT: add z1.b, z1.b, z1.b
; CHECK-NEXT: uunpklo z2.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z3.h, z1.b
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: uunpklo z1.h, z1.b
; CHECK-NEXT: uunpklo z4.s, z2.h
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: uunpklo z5.s, z3.h
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: uunpklo z6.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z2.s, z2.h
; CHECK-NEXT: uunpklo z7.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z3.s, z3.h
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z1.s, z1.h
; CHECK-NEXT: stp q4, q2, [x1, #64]
; CHECK-NEXT: stp q5, q3, [x1]
; CHECK-NEXT: stp q6, q0, [x1, #96]
; CHECK-NEXT: stp q7, q1, [x1, #32]
; CHECK-NEXT: ret
%a = load <32 x i8>, ptr %in
%b = add <32 x i8> %a, %a
%c = zext <32 x i8> %b to <32 x i32>
store <32 x i32> %c, ptr %out
ret void
}
;
; zext i8 -> i64
;
; NOTE: v4i8 is an unpacked typed stored within a v4i16 container. The zero
; extend is a two step process where the container is zero_extend_inreg'd with
; the result feeding a normal zero extend from halfs to doublewords.
define void @zext_v4i8_v4i64(<4 x i8> %a, ptr %out) {
; CHECK-LABEL: zext_v4i8_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: and z0.h, z0.h, #0xff
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z1.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = zext <4 x i8> %a to <4 x i64>
store <4 x i64>%b, ptr %out
ret void
}
define void @zext_v8i8_v8i64(<8 x i8> %a, ptr %out) {
; CHECK-LABEL: zext_v8i8_v8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: uunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z2.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z3.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z1.d, z1.s
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: stp q2, q1, [x0]
; CHECK-NEXT: stp q3, q0, [x0, #32]
; CHECK-NEXT: ret
%b = zext <8 x i8> %a to <8 x i64>
store <8 x i64>%b, ptr %out
ret void
}
define void @zext_v16i8_v16i64(<16 x i8> %a, ptr %out) {
; CHECK-LABEL: zext_v16i8_v16i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: uunpklo z1.h, z0.b
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: uunpklo z2.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z1.s, z1.h
; CHECK-NEXT: uunpklo z3.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z4.d, z2.s
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: mov z7.d, z1.d
; CHECK-NEXT: uunpklo z2.d, z2.s
; CHECK-NEXT: uunpklo z5.d, z3.s
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: ext z7.b, z7.b, z1.b, #8
; CHECK-NEXT: uunpklo z1.d, z1.s
; CHECK-NEXT: mov z6.d, z0.d
; CHECK-NEXT: uunpklo z3.d, z3.s
; CHECK-NEXT: stp q4, q2, [x0]
; CHECK-NEXT: uunpklo z4.d, z7.s
; CHECK-NEXT: ext z6.b, z6.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: stp q5, q3, [x0, #64]
; CHECK-NEXT: uunpklo z2.d, z6.s
; CHECK-NEXT: stp q1, q4, [x0, #32]
; CHECK-NEXT: stp q0, q2, [x0, #96]
; CHECK-NEXT: ret
%b = zext <16 x i8> %a to <16 x i64>
store <16 x i64> %b, ptr %out
ret void
}
define void @zext_v32i8_v32i64(ptr %in, ptr %out) {
; CHECK-LABEL: zext_v32i8_v32i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.b, z0.b, z0.b
; CHECK-NEXT: add z1.b, z1.b, z1.b
; CHECK-NEXT: mov z2.d, z0.d
; CHECK-NEXT: uunpklo z0.h, z0.b
; CHECK-NEXT: mov z3.d, z1.d
; CHECK-NEXT: uunpklo z1.h, z1.b
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: uunpklo z4.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z5.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z2.h, z2.b
; CHECK-NEXT: uunpklo z3.h, z3.b
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z16.d, z4.s
; CHECK-NEXT: ext z4.b, z4.b, z4.b, #8
; CHECK-NEXT: uunpklo z1.s, z1.h
; CHECK-NEXT: uunpklo z17.d, z5.s
; CHECK-NEXT: ext z5.b, z5.b, z5.b, #8
; CHECK-NEXT: uunpklo z6.s, z2.h
; CHECK-NEXT: uunpklo z7.s, z3.h
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: uunpklo z4.d, z4.s
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: uunpklo z19.d, z0.s
; CHECK-NEXT: uunpklo z5.d, z5.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z2.s, z2.h
; CHECK-NEXT: uunpklo z18.d, z6.s
; CHECK-NEXT: ext z6.b, z6.b, z6.b, #8
; CHECK-NEXT: uunpklo z3.s, z3.h
; CHECK-NEXT: stp q16, q4, [x1, #128]
; CHECK-NEXT: mov z16.d, z7.d
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: stp q17, q5, [x1]
; CHECK-NEXT: uunpklo z5.d, z7.s
; CHECK-NEXT: uunpklo z4.d, z6.s
; CHECK-NEXT: mov z6.d, z1.d
; CHECK-NEXT: ext z16.b, z16.b, z7.b, #8
; CHECK-NEXT: mov z7.d, z2.d
; CHECK-NEXT: stp q19, q0, [x1, #160]
; CHECK-NEXT: uunpklo z0.d, z2.s
; CHECK-NEXT: ext z6.b, z6.b, z1.b, #8
; CHECK-NEXT: uunpklo z1.d, z1.s
; CHECK-NEXT: stp q18, q4, [x1, #192]
; CHECK-NEXT: mov z4.d, z3.d
; CHECK-NEXT: ext z7.b, z7.b, z2.b, #8
; CHECK-NEXT: uunpklo z16.d, z16.s
; CHECK-NEXT: uunpklo z6.d, z6.s
; CHECK-NEXT: ext z4.b, z4.b, z3.b, #8
; CHECK-NEXT: uunpklo z2.d, z7.s
; CHECK-NEXT: uunpklo z3.d, z3.s
; CHECK-NEXT: stp q5, q16, [x1, #64]
; CHECK-NEXT: stp q1, q6, [x1, #32]
; CHECK-NEXT: uunpklo z1.d, z4.s
; CHECK-NEXT: stp q0, q2, [x1, #224]
; CHECK-NEXT: stp q3, q1, [x1, #96]
; CHECK-NEXT: ret
%a = load <32 x i8>, ptr %in
%b = add <32 x i8> %a, %a
%c = zext <32 x i8> %b to <32 x i64>
store <32 x i64> %c, ptr %out
ret void
}
;
; zext i16 -> i32
;
define void @zext_v8i16_v8i32(<8 x i16> %a, ptr %out) {
; CHECK-LABEL: zext_v8i16_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: uunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = zext <8 x i16> %a to <8 x i32>
store <8 x i32>%b, ptr %out
ret void
}
define void @zext_v16i16_v16i32(ptr %in, ptr %out) {
; CHECK-LABEL: zext_v16i16_v16i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.h, z0.h, z0.h
; CHECK-NEXT: add z1.h, z1.h, z1.h
; CHECK-NEXT: uunpklo z2.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z3.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z1.s, z1.h
; CHECK-NEXT: stp q2, q0, [x1, #32]
; CHECK-NEXT: stp q3, q1, [x1]
; CHECK-NEXT: ret
%a = load <16 x i16>, ptr %in
%b = add <16 x i16> %a, %a
%c = zext <16 x i16> %b to <16 x i32>
store <16 x i32> %c, ptr %out
ret void
}
;
; zext i16 -> i64
;
define void @zext_v4i16_v4i64(<4 x i16> %a, ptr %out) {
; CHECK-LABEL: zext_v4i16_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z1.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = zext <4 x i16> %a to <4 x i64>
store <4 x i64>%b, ptr %out
ret void
}
define void @zext_v8i16_v8i64(<8 x i16> %a, ptr %out) {
; CHECK-LABEL: zext_v8i16_v8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: uunpklo z1.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z2.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z1.d, z1.s
; CHECK-NEXT: uunpklo z3.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: stp q2, q1, [x0]
; CHECK-NEXT: stp q3, q0, [x0, #32]
; CHECK-NEXT: ret
%b = zext <8 x i16> %a to <8 x i64>
store <8 x i64>%b, ptr %out
ret void
}
define void @zext_v16i16_v16i64(ptr %in, ptr %out) {
; CHECK-LABEL: zext_v16i16_v16i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.h, z0.h, z0.h
; CHECK-NEXT: add z1.h, z1.h, z1.h
; CHECK-NEXT: uunpklo z2.s, z0.h
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z3.s, z1.h
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z0.s, z0.h
; CHECK-NEXT: uunpklo z1.s, z1.h
; CHECK-NEXT: uunpklo z4.d, z2.s
; CHECK-NEXT: ext z2.b, z2.b, z2.b, #8
; CHECK-NEXT: uunpklo z5.d, z3.s
; CHECK-NEXT: ext z3.b, z3.b, z3.b, #8
; CHECK-NEXT: uunpklo z6.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z2.d, z2.s
; CHECK-NEXT: uunpklo z7.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z3.d, z3.s
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: uunpklo z1.d, z1.s
; CHECK-NEXT: stp q4, q2, [x1, #64]
; CHECK-NEXT: stp q5, q3, [x1]
; CHECK-NEXT: stp q6, q0, [x1, #96]
; CHECK-NEXT: stp q7, q1, [x1, #32]
; CHECK-NEXT: ret
%a = load <16 x i16>, ptr %in
%b = add <16 x i16> %a, %a
%c = zext <16 x i16> %b to <16 x i64>
store <16 x i64> %c, ptr %out
ret void
}
;
; zext i32 -> i64
;
define void @zext_v4i32_v4i64(<4 x i32> %a, ptr %out) {
; CHECK-LABEL: zext_v4i32_v4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $q0 killed $q0 def $z0
; CHECK-NEXT: uunpklo z1.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: stp q1, q0, [x0]
; CHECK-NEXT: ret
%b = zext <4 x i32> %a to <4 x i64>
store <4 x i64>%b, ptr %out
ret void
}
define void @zext_v8i32_v8i64(ptr %in, ptr %out) {
; CHECK-LABEL: zext_v8i32_v8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldp q1, q0, [x0]
; CHECK-NEXT: add z0.s, z0.s, z0.s
; CHECK-NEXT: add z1.s, z1.s, z1.s
; CHECK-NEXT: uunpklo z2.d, z0.s
; CHECK-NEXT: ext z0.b, z0.b, z0.b, #8
; CHECK-NEXT: uunpklo z3.d, z1.s
; CHECK-NEXT: ext z1.b, z1.b, z1.b, #8
; CHECK-NEXT: uunpklo z0.d, z0.s
; CHECK-NEXT: uunpklo z1.d, z1.s
; CHECK-NEXT: stp q2, q0, [x1, #32]
; CHECK-NEXT: stp q3, q1, [x1]
; CHECK-NEXT: ret
%a = load <8 x i32>, ptr %in
%b = add <8 x i32> %a, %a
%c = zext <8 x i32> %b to <8 x i64>
store <8 x i64> %c, ptr %out
ret void
}
define void @extend_and_mul(i32 %0, <2 x i64> %1, ptr %2) {
; SVE-LABEL: extend_and_mul:
; SVE: // %bb.0:
; SVE-NEXT: mov z1.s, w0
; SVE-NEXT: ptrue p0.d, vl2
; SVE-NEXT: // kill: def $q0 killed $q0 def $z0
; SVE-NEXT: uunpklo z1.d, z1.s
; SVE-NEXT: mul z0.d, p0/m, z0.d, z1.d
; SVE-NEXT: str q0, [x1]
; SVE-NEXT: ret
;
; SVE2-LABEL: extend_and_mul:
; SVE2: // %bb.0:
; SVE2-NEXT: mov z1.s, w0
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
; SVE2-NEXT: uunpklo z1.d, z1.s
; SVE2-NEXT: mul z0.d, z1.d, z0.d
; SVE2-NEXT: str q0, [x1]
; SVE2-NEXT: ret
%broadcast.splatinsert2 = insertelement <2 x i32> poison, i32 %0, i64 0
%broadcast.splat3 = shufflevector <2 x i32> %broadcast.splatinsert2, <2 x i32> poison, <2 x i32> zeroinitializer
%4 = zext <2 x i32> %broadcast.splat3 to <2 x i64>
%5 = mul <2 x i64> %4, %1
store <2 x i64> %5, ptr %2, align 2
ret void
}
define void @extend_no_mul(i32 %0, <2 x i64> %1, ptr %2) {
; CHECK-LABEL: extend_no_mul:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov w8, w0
; CHECK-NEXT: mov z0.d, x8
; CHECK-NEXT: str q0, [x1]
; CHECK-NEXT: ret
entry:
%broadcast.splatinsert2 = insertelement <2 x i32> poison, i32 %0, i64 0
%broadcast.splat3 = shufflevector <2 x i32> %broadcast.splatinsert2, <2 x i32> poison, <2 x i32> zeroinitializer
%3 = zext <2 x i32> %broadcast.splat3 to <2 x i64>
store <2 x i64> %3, ptr %2, align 2
ret void
}