| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s |
| |
| ; |
| ; SQSUB |
| ; |
| |
| define <vscale x 16 x i8> @sqsub_i8_u(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: sqsub_i8_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: sqsub z0.b, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.u.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @sqsub_i16_u(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: sqsub_i16_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: sqsub z0.h, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.u.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @sqsub_i32_u(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: sqsub_i32_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: sqsub z0.s, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.u.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @sqsub_i64_u(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: sqsub_i64_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: sqsub z0.d, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.u.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| ; |
| ; UQSUB |
| ; |
| |
| define <vscale x 16 x i8> @uqsub_i8_u(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) { |
| ; CHECK-LABEL: uqsub_i8_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: uqsub z0.b, z0.b, z1.b |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.u.nxv16i8(<vscale x 16 x i1> %pg, |
| <vscale x 16 x i8> %a, |
| <vscale x 16 x i8> %b) |
| ret <vscale x 16 x i8> %out |
| } |
| |
| define <vscale x 8 x i16> @uqsub_i16_u(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) { |
| ; CHECK-LABEL: uqsub_i16_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: uqsub z0.h, z0.h, z1.h |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.u.nxv8i16(<vscale x 8 x i1> %pg, |
| <vscale x 8 x i16> %a, |
| <vscale x 8 x i16> %b) |
| ret <vscale x 8 x i16> %out |
| } |
| |
| define <vscale x 4 x i32> @uqsub_i32_u(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) { |
| ; CHECK-LABEL: uqsub_i32_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: uqsub z0.s, z0.s, z1.s |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.u.nxv4i32(<vscale x 4 x i1> %pg, |
| <vscale x 4 x i32> %a, |
| <vscale x 4 x i32> %b) |
| ret <vscale x 4 x i32> %out |
| } |
| |
| define <vscale x 2 x i64> @uqsub_i64_u(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) { |
| ; CHECK-LABEL: uqsub_i64_u: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: uqsub z0.d, z0.d, z1.d |
| ; CHECK-NEXT: ret |
| %out = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.u.nxv2i64(<vscale x 2 x i1> %pg, |
| <vscale x 2 x i64> %a, |
| <vscale x 2 x i64> %b) |
| ret <vscale x 2 x i64> %out |
| } |
| |
| declare <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.u.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.uqsub.u.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.uqsub.u.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.uqsub.u.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.sqsub.u.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.sqsub.u.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.sqsub.u.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.sqsub.u.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) |