| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -mattr=+use-experimental-zeroing-pseudos < %s | FileCheck %s |
| |
| ; |
| ; ADD |
| ; |
| |
| define <vscale x 16 x i8> @add_i8_zero(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: add_i8_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.b, p0/z, z0.b |
| ; CHECK-NEXT: add z0.b, p0/m, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a_z, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @add_i16_zero(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: add_i16_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.h, p0/z, z0.h |
| ; CHECK-NEXT: add z0.h, p0/m, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a_z, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @add_i32_zero(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: add_i32_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.s, p0/z, z0.s |
| ; CHECK-NEXT: add z0.s, p0/m, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a_z, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @add_i64_zero(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: add_i64_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: add z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; |
| ; SUB |
| ; |
| |
| define <vscale x 16 x i8> @sub_i8_zero(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: sub_i8_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.b, p0/z, z0.b |
| ; CHECK-NEXT: sub z0.b, p0/m, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a_z, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @sub_i16_zero(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: sub_i16_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.h, p0/z, z0.h |
| ; CHECK-NEXT: sub z0.h, p0/m, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a_z, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @sub_i32_zero(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: sub_i32_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.s, p0/z, z0.s |
| ; CHECK-NEXT: sub z0.s, p0/m, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a_z, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @sub_i64_zero(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: sub_i64_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: sub z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; |
| ; SUBR |
| ; |
| |
| define <vscale x 16 x i8> @subr_i8_zero(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: subr_i8_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.b, p0/z, z0.b |
| ; CHECK-NEXT: subr z0.b, p0/m, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a_z, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @subr_i16_zero(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: subr_i16_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.h, p0/z, z0.h |
| ; CHECK-NEXT: subr z0.h, p0/m, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a_z, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @subr_i32_zero(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: subr_i32_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.s, p0/z, z0.s |
| ; CHECK-NEXT: subr z0.s, p0/m, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a_z, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @subr_i64_zero(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: subr_i64_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: subr z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; |
| ; ORR |
| ; |
| |
| define <vscale x 16 x i8> @orr_i8_zero(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: orr_i8_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.b, p0/z, z0.b |
| ; CHECK-NEXT: orr z0.b, p0/m, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a_z, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @orr_i16_zero(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: orr_i16_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.h, p0/z, z0.h |
| ; CHECK-NEXT: orr z0.h, p0/m, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a_z, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @orr_i32_zero(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: orr_i32_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.s, p0/z, z0.s |
| ; CHECK-NEXT: orr z0.s, p0/m, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a_z, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @orr_i64_zero(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: orr_i64_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: orr z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; |
| ; EOR |
| ; |
| |
| define <vscale x 16 x i8> @eor_i8_zero(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: eor_i8_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.b, p0/z, z0.b |
| ; CHECK-NEXT: eor z0.b, p0/m, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a_z, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @eor_i16_zero(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: eor_i16_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.h, p0/z, z0.h |
| ; CHECK-NEXT: eor z0.h, p0/m, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a_z, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @eor_i32_zero(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: eor_i32_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.s, p0/z, z0.s |
| ; CHECK-NEXT: eor z0.s, p0/m, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a_z, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @eor_i64_zero(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: eor_i64_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: eor z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; |
| ; AND |
| ; |
| |
| define <vscale x 16 x i8> @and_i8_zero(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: and_i8_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.b, p0/z, z0.b |
| ; CHECK-NEXT: and z0.b, p0/m, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a_z, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @and_i16_zero(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: and_i16_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.h, p0/z, z0.h |
| ; CHECK-NEXT: and z0.h, p0/m, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a_z, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @and_i32_zero(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: and_i32_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.s, p0/z, z0.s |
| ; CHECK-NEXT: and z0.s, p0/m, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a_z, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @and_i64_zero(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: and_i64_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: and z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; |
| ; BIC |
| ; |
| |
| define <vscale x 16 x i8> @bic_i8_zero(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: bic_i8_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.b, p0/z, z0.b |
| ; CHECK-NEXT: bic z0.b, p0/m, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> zeroinitializer |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a_z, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @bic_i16_zero(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: bic_i16_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.h, p0/z, z0.h |
| ; CHECK-NEXT: bic z0.h, p0/m, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> zeroinitializer |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a_z, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @bic_i32_zero(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: bic_i32_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.s, p0/z, z0.s |
| ; CHECK-NEXT: bic z0.s, p0/m, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> zeroinitializer |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a_z, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @bic_i64_zero(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: bic_i64_zero: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: bic z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; BIC (i.e. A & ~A) is illegal operation with movprfx, so the codegen depend on IR before expand-pseudo |
| define <vscale x 2 x i64> @bic_i64_zero_no_unique_reg(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) { |
| ; CHECK-LABEL: bic_i64_zero_no_unique_reg: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mov z1.d, #0 // =0x0 |
| ; CHECK-NEXT: mov z1.d, p0/m, z0.d |
| ; CHECK-NEXT: movprfx z0.d, p0/z, z0.d |
| ; CHECK-NEXT: bic z0.d, p0/m, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a_z, |
| <vscale x 2 x i64> %a_z) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; BIC (i.e. A & ~B) is not a commutative operation, so disable it when the |
| ; destination operand is not the destructive operand |
| define <vscale x 2 x i64> @bic_i64_zero_no_comm(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: bic_i64_zero_no_comm: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mov z2.d, #0 // =0x0 |
| ; CHECK-NEXT: mov z2.d, p0/m, z0.d |
| ; CHECK-NEXT: mov z0.d, z1.d |
| ; CHECK-NEXT: bic z0.d, p0/m, z0.d, z2.d |
| ; CHECK-NEXT: ret |
| %a_z = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> zeroinitializer |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %b, |
| <vscale x 2 x i64> %a_z) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>) |
| declare <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) |
| declare <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) |
| declare <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>) |
| declare <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) |
| declare <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) |
| declare <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>) |
| declare <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) |
| declare <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) |
| declare <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>) |
| declare <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) |
| declare <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) |
| declare <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>) |
| declare <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) |
| declare <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) |
| declare <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>) |
| declare <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) |
| declare <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) |
| declare <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>) |
| declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) |
| declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) |
| declare <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |