derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
626 lines
20 KiB
LLVM
626 lines
20 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
|
|
|
|
define <vscale x 16 x i8> @sext_i1_i8(<vscale x 16 x i1> %a) {
|
|
; CHECK-LABEL: sext_i1_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.b, p0/z, #-1 // =0xffffffffffffffff
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 16 x i1> %a to <vscale x 16 x i8>
|
|
ret <vscale x 16 x i8> %r
|
|
}
|
|
|
|
define <vscale x 8 x i16> @sext_i1_i16(<vscale x 8 x i1> %a) {
|
|
; CHECK-LABEL: sext_i1_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.h, p0/z, #-1 // =0xffffffffffffffff
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 8 x i1> %a to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %r
|
|
}
|
|
|
|
define <vscale x 4 x i32> @sext_i1_i32(<vscale x 4 x i1> %a) {
|
|
; CHECK-LABEL: sext_i1_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.s, p0/z, #-1 // =0xffffffffffffffff
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 4 x i1> %a to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sext_i1_i64(<vscale x 2 x i1> %a) {
|
|
; CHECK-LABEL: sext_i1_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.d, p0/z, #-1 // =0xffffffffffffffff
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 2 x i1> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 16 x i8> @zext_i1_i8(<vscale x 16 x i1> %a) {
|
|
; CHECK-LABEL: zext_i1_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.b, p0/z, #1 // =0x1
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 16 x i1> %a to <vscale x 16 x i8>
|
|
ret <vscale x 16 x i8> %r
|
|
}
|
|
|
|
define <vscale x 8 x i16> @zext_i1_i16(<vscale x 8 x i1> %a) {
|
|
; CHECK-LABEL: zext_i1_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.h, p0/z, #1 // =0x1
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 8 x i1> %a to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %r
|
|
}
|
|
|
|
define <vscale x 4 x i32> @zext_i1_i32(<vscale x 4 x i1> %a) {
|
|
; CHECK-LABEL: zext_i1_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.s, p0/z, #1 // =0x1
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 4 x i1> %a to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_i1_i64(<vscale x 2 x i1> %a) {
|
|
; CHECK-LABEL: zext_i1_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov z0.d, p0/z, #1 // =0x1
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 2 x i1> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 8 x i16> @sext_i8_i16(<vscale x 8 x i8> %a) {
|
|
; CHECK-LABEL: sext_i8_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: sxtb z0.h, p0/m, z0.h
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %r
|
|
}
|
|
|
|
define <vscale x 4 x i32> @sext_i8_i32(<vscale x 4 x i8> %a) {
|
|
; CHECK-LABEL: sext_i8_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: sxtb z0.s, p0/m, z0.s
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 4 x i8> %a to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sext_i8_i64(<vscale x 2 x i8> %a) {
|
|
; CHECK-LABEL: sext_i8_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: sxtb z0.d, p0/m, z0.d
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 2 x i8> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 8 x i16> @zext_i8_i16(<vscale x 8 x i8> %a) {
|
|
; CHECK-LABEL: zext_i8_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.h, z0.h, #0xff
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 8 x i8> %a to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %r
|
|
}
|
|
|
|
define <vscale x 4 x i32> @zext_i8_i32(<vscale x 4 x i8> %a) {
|
|
; CHECK-LABEL: zext_i8_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.s, z0.s, #0xff
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 4 x i8> %a to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_i8_i64(<vscale x 2 x i8> %a) {
|
|
; CHECK-LABEL: zext_i8_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.d, z0.d, #0xff
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 2 x i8> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 4 x i32> @sext_i16_i32(<vscale x 4 x i16> %a) {
|
|
; CHECK-LABEL: sext_i16_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: sxth z0.s, p0/m, z0.s
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 4 x i16> %a to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sext_i16_i64(<vscale x 2 x i16> %a) {
|
|
; CHECK-LABEL: sext_i16_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: sxth z0.d, p0/m, z0.d
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 2 x i16> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 4 x i32> @zext_i16_i32(<vscale x 4 x i16> %a) {
|
|
; CHECK-LABEL: zext_i16_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.s, z0.s, #0xffff
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 4 x i16> %a to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_i16_i64(<vscale x 2 x i16> %a) {
|
|
; CHECK-LABEL: zext_i16_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.d, z0.d, #0xffff
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 2 x i16> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sext_i32_i64(<vscale x 2 x i32> %a) {
|
|
; CHECK-LABEL: sext_i32_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: sxtw z0.d, p0/m, z0.d
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 2 x i32> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_i32_i64(<vscale x 2 x i32> %a) {
|
|
; CHECK-LABEL: zext_i32_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.d, z0.d, #0xffffffff
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 2 x i32> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
; Extending to illegal types
|
|
|
|
define <vscale x 16 x i16> @sext_b_to_h(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_b_to_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z2.h, z0.b
|
|
; CHECK-NEXT: sunpkhi z1.h, z0.b
|
|
; CHECK-NEXT: mov z0.d, z2.d
|
|
; CHECK-NEXT: ret
|
|
%ext = sext <vscale x 16 x i8> %a to <vscale x 16 x i16>
|
|
ret <vscale x 16 x i16> %ext
|
|
}
|
|
|
|
define <vscale x 8 x i32> @sext_h_to_s(<vscale x 8 x i16> %a) {
|
|
; CHECK-LABEL: sext_h_to_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z2.s, z0.h
|
|
; CHECK-NEXT: sunpkhi z1.s, z0.h
|
|
; CHECK-NEXT: mov z0.d, z2.d
|
|
; CHECK-NEXT: ret
|
|
%ext = sext <vscale x 8 x i16> %a to <vscale x 8 x i32>
|
|
ret <vscale x 8 x i32> %ext
|
|
}
|
|
|
|
define <vscale x 4 x i64> @sext_s_to_d(<vscale x 4 x i32> %a) {
|
|
; CHECK-LABEL: sext_s_to_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z2.d, z0.s
|
|
; CHECK-NEXT: sunpkhi z1.d, z0.s
|
|
; CHECK-NEXT: mov z0.d, z2.d
|
|
; CHECK-NEXT: ret
|
|
%ext = sext <vscale x 4 x i32> %a to <vscale x 4 x i64>
|
|
ret <vscale x 4 x i64> %ext
|
|
}
|
|
|
|
define <vscale x 16 x i32> @sext_b_to_s(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_b_to_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z1.h, z0.b
|
|
; CHECK-NEXT: sunpkhi z3.h, z0.b
|
|
; CHECK-NEXT: sunpklo z0.s, z1.h
|
|
; CHECK-NEXT: sunpkhi z1.s, z1.h
|
|
; CHECK-NEXT: sunpklo z2.s, z3.h
|
|
; CHECK-NEXT: sunpkhi z3.s, z3.h
|
|
; CHECK-NEXT: ret
|
|
%ext = sext <vscale x 16 x i8> %a to <vscale x 16 x i32>
|
|
ret <vscale x 16 x i32> %ext
|
|
}
|
|
|
|
define <vscale x 16 x i64> @sext_b_to_d(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_b_to_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z1.h, z0.b
|
|
; CHECK-NEXT: sunpkhi z0.h, z0.b
|
|
; CHECK-NEXT: sunpklo z2.s, z1.h
|
|
; CHECK-NEXT: sunpkhi z3.s, z1.h
|
|
; CHECK-NEXT: sunpklo z5.s, z0.h
|
|
; CHECK-NEXT: sunpkhi z7.s, z0.h
|
|
; CHECK-NEXT: sunpklo z0.d, z2.s
|
|
; CHECK-NEXT: sunpkhi z1.d, z2.s
|
|
; CHECK-NEXT: sunpklo z2.d, z3.s
|
|
; CHECK-NEXT: sunpkhi z3.d, z3.s
|
|
; CHECK-NEXT: sunpklo z4.d, z5.s
|
|
; CHECK-NEXT: sunpkhi z5.d, z5.s
|
|
; CHECK-NEXT: sunpklo z6.d, z7.s
|
|
; CHECK-NEXT: sunpkhi z7.d, z7.s
|
|
; CHECK-NEXT: ret
|
|
%ext = sext <vscale x 16 x i8> %a to <vscale x 16 x i64>
|
|
ret <vscale x 16 x i64> %ext
|
|
}
|
|
|
|
define <vscale x 16 x i16> @zext_b_to_h(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: zext_b_to_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z2.h, z0.b
|
|
; CHECK-NEXT: uunpkhi z1.h, z0.b
|
|
; CHECK-NEXT: mov z0.d, z2.d
|
|
; CHECK-NEXT: ret
|
|
%ext = zext <vscale x 16 x i8> %a to <vscale x 16 x i16>
|
|
ret <vscale x 16 x i16> %ext
|
|
}
|
|
|
|
define <vscale x 8 x i32> @zext_h_to_s(<vscale x 8 x i16> %a) {
|
|
; CHECK-LABEL: zext_h_to_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z2.s, z0.h
|
|
; CHECK-NEXT: uunpkhi z1.s, z0.h
|
|
; CHECK-NEXT: mov z0.d, z2.d
|
|
; CHECK-NEXT: ret
|
|
%ext = zext <vscale x 8 x i16> %a to <vscale x 8 x i32>
|
|
ret <vscale x 8 x i32> %ext
|
|
}
|
|
|
|
define <vscale x 4 x i64> @zext_s_to_d(<vscale x 4 x i32> %a) {
|
|
; CHECK-LABEL: zext_s_to_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z2.d, z0.s
|
|
; CHECK-NEXT: uunpkhi z1.d, z0.s
|
|
; CHECK-NEXT: mov z0.d, z2.d
|
|
; CHECK-NEXT: ret
|
|
%ext = zext <vscale x 4 x i32> %a to <vscale x 4 x i64>
|
|
ret <vscale x 4 x i64> %ext
|
|
}
|
|
|
|
define <vscale x 16 x i32> @zext_b_to_s(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: zext_b_to_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z1.h, z0.b
|
|
; CHECK-NEXT: uunpkhi z3.h, z0.b
|
|
; CHECK-NEXT: uunpklo z0.s, z1.h
|
|
; CHECK-NEXT: uunpkhi z1.s, z1.h
|
|
; CHECK-NEXT: uunpklo z2.s, z3.h
|
|
; CHECK-NEXT: uunpkhi z3.s, z3.h
|
|
; CHECK-NEXT: ret
|
|
%ext = zext <vscale x 16 x i8> %a to <vscale x 16 x i32>
|
|
ret <vscale x 16 x i32> %ext
|
|
}
|
|
|
|
define <vscale x 16 x i64> @zext_b_to_d(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: zext_b_to_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z1.h, z0.b
|
|
; CHECK-NEXT: uunpkhi z0.h, z0.b
|
|
; CHECK-NEXT: uunpklo z2.s, z1.h
|
|
; CHECK-NEXT: uunpkhi z3.s, z1.h
|
|
; CHECK-NEXT: uunpklo z5.s, z0.h
|
|
; CHECK-NEXT: uunpkhi z7.s, z0.h
|
|
; CHECK-NEXT: uunpklo z0.d, z2.s
|
|
; CHECK-NEXT: uunpkhi z1.d, z2.s
|
|
; CHECK-NEXT: uunpklo z2.d, z3.s
|
|
; CHECK-NEXT: uunpkhi z3.d, z3.s
|
|
; CHECK-NEXT: uunpklo z4.d, z5.s
|
|
; CHECK-NEXT: uunpkhi z5.d, z5.s
|
|
; CHECK-NEXT: uunpklo z6.d, z7.s
|
|
; CHECK-NEXT: uunpkhi z7.d, z7.s
|
|
; CHECK-NEXT: ret
|
|
%ext = zext <vscale x 16 x i8> %a to <vscale x 16 x i64>
|
|
ret <vscale x 16 x i64> %ext
|
|
}
|
|
|
|
; Extending unpacked data to wide, illegal types
|
|
|
|
define <vscale x 4 x i64> @zext_4i8_4i64(<vscale x 4 x i8> %aval) {
|
|
; CHECK-LABEL: zext_4i8_4i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: movprfx z1, z0
|
|
; CHECK-NEXT: and z1.s, z1.s, #0xff
|
|
; CHECK-NEXT: uunpklo z0.d, z1.s
|
|
; CHECK-NEXT: uunpkhi z1.d, z1.s
|
|
; CHECK-NEXT: ret
|
|
%aext = zext <vscale x 4 x i8> %aval to <vscale x 4 x i64>
|
|
ret <vscale x 4 x i64> %aext
|
|
}
|
|
|
|
define <vscale x 4 x i64> @zext_4i16_4i64(<vscale x 4 x i16> %aval) {
|
|
; CHECK-LABEL: zext_4i16_4i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: movprfx z1, z0
|
|
; CHECK-NEXT: and z1.s, z1.s, #0xffff
|
|
; CHECK-NEXT: uunpklo z0.d, z1.s
|
|
; CHECK-NEXT: uunpkhi z1.d, z1.s
|
|
; CHECK-NEXT: ret
|
|
%aext = zext <vscale x 4 x i16> %aval to <vscale x 4 x i64>
|
|
ret <vscale x 4 x i64> %aext
|
|
}
|
|
|
|
define <vscale x 8 x i32> @zext_8i8_8i32(<vscale x 8 x i8> %aval) {
|
|
; CHECK-LABEL: zext_8i8_8i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: movprfx z1, z0
|
|
; CHECK-NEXT: and z1.h, z1.h, #0xff
|
|
; CHECK-NEXT: uunpklo z0.s, z1.h
|
|
; CHECK-NEXT: uunpkhi z1.s, z1.h
|
|
; CHECK-NEXT: ret
|
|
%aext = zext <vscale x 8 x i8> %aval to <vscale x 8 x i32>
|
|
ret <vscale x 8 x i32> %aext
|
|
}
|
|
|
|
define <vscale x 8 x i64> @zext_8i8_8i64(<vscale x 8 x i8> %aval) {
|
|
; CHECK-LABEL: zext_8i8_8i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.h, z0.h, #0xff
|
|
; CHECK-NEXT: uunpklo z1.s, z0.h
|
|
; CHECK-NEXT: uunpkhi z3.s, z0.h
|
|
; CHECK-NEXT: uunpklo z0.d, z1.s
|
|
; CHECK-NEXT: uunpkhi z1.d, z1.s
|
|
; CHECK-NEXT: uunpklo z2.d, z3.s
|
|
; CHECK-NEXT: uunpkhi z3.d, z3.s
|
|
; CHECK-NEXT: ret
|
|
%aext = zext <vscale x 8 x i8> %aval to <vscale x 8 x i64>
|
|
ret <vscale x 8 x i64> %aext
|
|
}
|
|
|
|
define <vscale x 4 x i64> @sext_4i8_4i64(<vscale x 4 x i8> %aval) {
|
|
; CHECK-LABEL: sext_4i8_4i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: movprfx z1, z0
|
|
; CHECK-NEXT: sxtb z1.s, p0/m, z0.s
|
|
; CHECK-NEXT: sunpklo z0.d, z1.s
|
|
; CHECK-NEXT: sunpkhi z1.d, z1.s
|
|
; CHECK-NEXT: ret
|
|
%aext = sext <vscale x 4 x i8> %aval to <vscale x 4 x i64>
|
|
ret <vscale x 4 x i64> %aext
|
|
}
|
|
|
|
define <vscale x 4 x i64> @sext_4i16_4i64(<vscale x 4 x i16> %aval) {
|
|
; CHECK-LABEL: sext_4i16_4i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: movprfx z1, z0
|
|
; CHECK-NEXT: sxth z1.s, p0/m, z0.s
|
|
; CHECK-NEXT: sunpklo z0.d, z1.s
|
|
; CHECK-NEXT: sunpkhi z1.d, z1.s
|
|
; CHECK-NEXT: ret
|
|
%aext = sext <vscale x 4 x i16> %aval to <vscale x 4 x i64>
|
|
ret <vscale x 4 x i64> %aext
|
|
}
|
|
|
|
define <vscale x 8 x i32> @sext_8i8_8i32(<vscale x 8 x i8> %aval) {
|
|
; CHECK-LABEL: sext_8i8_8i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: movprfx z1, z0
|
|
; CHECK-NEXT: sxtb z1.h, p0/m, z0.h
|
|
; CHECK-NEXT: sunpklo z0.s, z1.h
|
|
; CHECK-NEXT: sunpkhi z1.s, z1.h
|
|
; CHECK-NEXT: ret
|
|
%aext = sext <vscale x 8 x i8> %aval to <vscale x 8 x i32>
|
|
ret <vscale x 8 x i32> %aext
|
|
}
|
|
|
|
define <vscale x 8 x i64> @sext_8i8_8i64(<vscale x 8 x i8> %aval) {
|
|
; CHECK-LABEL: sext_8i8_8i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: sxtb z0.h, p0/m, z0.h
|
|
; CHECK-NEXT: sunpklo z1.s, z0.h
|
|
; CHECK-NEXT: sunpkhi z3.s, z0.h
|
|
; CHECK-NEXT: sunpklo z0.d, z1.s
|
|
; CHECK-NEXT: sunpkhi z1.d, z1.s
|
|
; CHECK-NEXT: sunpklo z2.d, z3.s
|
|
; CHECK-NEXT: sunpkhi z3.d, z3.s
|
|
; CHECK-NEXT: ret
|
|
%aext = sext <vscale x 8 x i8> %aval to <vscale x 8 x i64>
|
|
ret <vscale x 8 x i64> %aext
|
|
}
|
|
|
|
|
|
; Extending non power-of-two types
|
|
|
|
define <vscale x 2 x i64> @sext_i18_i64(<vscale x 2 x i18> %a) {
|
|
; CHECK-LABEL: sext_i18_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: lsl z0.d, z0.d, #46
|
|
; CHECK-NEXT: asr z0.d, z0.d, #46
|
|
; CHECK-NEXT: ret
|
|
%r = sext <vscale x 2 x i18> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_i18_i64(<vscale x 2 x i18> %a) {
|
|
; CHECK-LABEL: zext_i18_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: and z0.d, z0.d, #0x3ffff
|
|
; CHECK-NEXT: ret
|
|
%r = zext <vscale x 2 x i18> %a to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %r
|
|
}
|
|
|
|
define <vscale x 8 x i16> @sext_inreg_i16_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_inreg_i16_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z0.h, z0.b
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 8 x i8> @llvm.vector.extract.nxv8i8.nxv16i8(<vscale x 16 x i8> %a, i64 0)
|
|
%sext = sext <vscale x 8 x i8> %subvec to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %sext
|
|
}
|
|
|
|
define <vscale x 4 x i32> @sext_inreg_i32_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_inreg_i32_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z0.h, z0.b
|
|
; CHECK-NEXT: sunpklo z0.s, z0.h
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 4 x i8> @llvm.vector.extract.nxv4i8.nxv16i8(<vscale x 16 x i8> %a, i64 0)
|
|
%sext = sext <vscale x 4 x i8> %subvec to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %sext
|
|
}
|
|
|
|
define <vscale x 4 x i32> @sext_inreg_i32_from_i16(<vscale x 8 x i16> %a) {
|
|
; CHECK-LABEL: sext_inreg_i32_from_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z0.s, z0.h
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 4 x i16> @llvm.vector.extract.nxv4i16.nxv8i16(<vscale x 8 x i16> %a, i64 0)
|
|
%sext = sext <vscale x 4 x i16> %subvec to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %sext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sext_inreg_i64_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_inreg_i64_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z0.h, z0.b
|
|
; CHECK-NEXT: sunpklo z0.s, z0.h
|
|
; CHECK-NEXT: sunpklo z0.d, z0.s
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 2 x i8> @llvm.vector.extract.nxv2i8.nxv16i8(<vscale x 16 x i8> %a, i64 0)
|
|
%sext = sext <vscale x 2 x i8> %subvec to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %sext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sext_inreg_i64_from_i16(<vscale x 8 x i16> %a) {
|
|
; CHECK-LABEL: sext_inreg_i64_from_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z0.s, z0.h
|
|
; CHECK-NEXT: sunpklo z0.d, z0.s
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 2 x i16> @llvm.vector.extract.nxv2i16.nxv8i16(<vscale x 8 x i16> %a, i64 0)
|
|
%sext = sext <vscale x 2 x i16> %subvec to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %sext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @sext_inreg_i64_from_i32(<vscale x 4 x i32> %a) {
|
|
; CHECK-LABEL: sext_inreg_i64_from_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sunpklo z0.d, z0.s
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 2 x i32> @llvm.vector.extract.nxv2i32.nxv4i32(<vscale x 4 x i32> %a, i64 0)
|
|
%sext = sext <vscale x 2 x i32> %subvec to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %sext
|
|
}
|
|
|
|
define <vscale x 8 x i16> @zext_inreg_i16_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: zext_inreg_i16_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z0.h, z0.b
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 8 x i8> @llvm.vector.extract.nxv8i8.nxv16i8(<vscale x 16 x i8> %a, i64 0)
|
|
%zext = zext <vscale x 8 x i8> %subvec to <vscale x 8 x i16>
|
|
ret <vscale x 8 x i16> %zext
|
|
}
|
|
|
|
define <vscale x 4 x i32> @zext_inreg_i32_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: zext_inreg_i32_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z0.h, z0.b
|
|
; CHECK-NEXT: uunpklo z0.s, z0.h
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 4 x i8> @llvm.vector.extract.nxv4i8.nxv16i8(<vscale x 16 x i8> %a, i64 0)
|
|
%zext = zext <vscale x 4 x i8> %subvec to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %zext
|
|
}
|
|
|
|
define <vscale x 4 x i32> @zext_inreg_i32_from_i16(<vscale x 8 x i16> %a) {
|
|
; CHECK-LABEL: zext_inreg_i32_from_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z0.s, z0.h
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 4 x i16> @llvm.vector.extract.nxv4i16.nxv8i16(<vscale x 8 x i16> %a, i64 0)
|
|
%zext = zext <vscale x 4 x i16> %subvec to <vscale x 4 x i32>
|
|
ret <vscale x 4 x i32> %zext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_inreg_i64_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: zext_inreg_i64_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z0.h, z0.b
|
|
; CHECK-NEXT: uunpklo z0.s, z0.h
|
|
; CHECK-NEXT: uunpklo z0.d, z0.s
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 2 x i8> @llvm.vector.extract.nxv2i8.nxv16i8(<vscale x 16 x i8> %a, i64 0)
|
|
%zext = zext <vscale x 2 x i8> %subvec to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %zext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_inreg_i64_from_i16(<vscale x 8 x i16> %a) {
|
|
; CHECK-LABEL: zext_inreg_i64_from_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z0.s, z0.h
|
|
; CHECK-NEXT: uunpklo z0.d, z0.s
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 2 x i16> @llvm.vector.extract.nxv2i16.nxv8i16(<vscale x 8 x i16> %a, i64 0)
|
|
%zext = zext <vscale x 2 x i16> %subvec to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %zext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @zext_inreg_i64_from_i32(<vscale x 4 x i32> %a) {
|
|
; CHECK-LABEL: zext_inreg_i64_from_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uunpklo z0.d, z0.s
|
|
; CHECK-NEXT: ret
|
|
%subvec = call <vscale x 2 x i32> @llvm.vector.extract.nxv2i32.nxv4i32(<vscale x 4 x i32> %a, i64 0)
|
|
%zext = zext <vscale x 2 x i32> %subvec to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %zext
|
|
}
|
|
|
|
; Sign-extend-inreg from i8 -> i1 -> i16
|
|
define <vscale x 16 x i16> @sext_inreg_i1_to_i16_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_inreg_i1_to_i16_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: lsl z0.b, z0.b, #7
|
|
; CHECK-NEXT: asr z1.b, z0.b, #7
|
|
; CHECK-NEXT: sunpklo z0.h, z1.b
|
|
; CHECK-NEXT: sunpkhi z1.h, z1.b
|
|
; CHECK-NEXT: ret
|
|
%a.trunc = trunc <vscale x 16 x i8> %a to <vscale x 16 x i1>
|
|
%a.sextinreg = sext <vscale x 16 x i1> %a.trunc to <vscale x 16 x i16>
|
|
ret <vscale x 16 x i16> %a.sextinreg
|
|
}
|
|
|
|
; Sign-extend-inreg from i8 -> i2 -> i16
|
|
define <vscale x 16 x i16> @sext_inreg_i2_to_i16_from_i8(<vscale x 16 x i8> %a) {
|
|
; CHECK-LABEL: sext_inreg_i2_to_i16_from_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: lsl z0.b, z0.b, #6
|
|
; CHECK-NEXT: asr z1.b, z0.b, #6
|
|
; CHECK-NEXT: sunpklo z0.h, z1.b
|
|
; CHECK-NEXT: sunpkhi z1.h, z1.b
|
|
; CHECK-NEXT: ret
|
|
%a.trunc = trunc <vscale x 16 x i8> %a to <vscale x 16 x i2>
|
|
%a.sextinreg = sext <vscale x 16 x i2> %a.trunc to <vscale x 16 x i16>
|
|
ret <vscale x 16 x i16> %a.sextinreg
|
|
}
|
|
|
|
define <vscale x 7 x i16> @widen_sext_inreg_result(<vscale x 7 x i16> %a) {
|
|
; CHECK-LABEL: widen_sext_inreg_result:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: sxtb z0.h, p0/m, z0.h
|
|
; CHECK-NEXT: ret
|
|
%a.trunc = trunc <vscale x 7 x i16> %a to <vscale x 7 x i8>
|
|
%a.sextinreg = sext <vscale x 7 x i8> %a.trunc to <vscale x 7 x i16>
|
|
ret <vscale x 7 x i16> %a.sextinreg
|
|
}
|