| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc -verify-machineinstrs < %s 2>%t | FileCheck --check-prefix=CHECK --check-prefix=CHECK-SELDAG %s |
| ; RUN: llc -verify-machineinstrs -O0 < %s 2>%t | FileCheck --check-prefix=CHECK --check-prefix=CHECK-FASTISEL %s |
| |
| ; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t |
| |
| ; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it. |
| ; WARN-NOT: warning |
| |
| |
| target triple = "aarch64-unknown-linux-gnu" |
| |
| ; |
| ; VECTOR_REVERSE |
| ; |
| |
| define <16 x i8> @reverse_v16i8(<16 x i8> %a) #0 { |
| ; CHECK-LABEL: .LCPI0_0: |
| ; CHECK: .byte 15 // 0xf |
| ; CHECK-NEXT: .byte 14 // 0xe |
| ; CHECK-NEXT: .byte 13 // 0xd |
| ; CHECK-NEXT: .byte 12 // 0xc |
| ; CHECK-NEXT: .byte 11 // 0xb |
| ; CHECK-NEXT: .byte 10 // 0xa |
| ; CHECK-NEXT: .byte 9 // 0x9 |
| ; CHECK-NEXT: .byte 8 // 0x8 |
| ; CHECK-NEXT: .byte 7 // 0x7 |
| ; CHECK-NEXT: .byte 6 // 0x6 |
| ; CHECK-NEXT: .byte 5 // 0x5 |
| ; CHECK-NEXT: .byte 4 // 0x4 |
| ; CHECK-NEXT: .byte 3 // 0x3 |
| ; CHECK-NEXT: .byte 2 // 0x2 |
| ; CHECK-NEXT: .byte 1 // 0x1 |
| ; CHECK-NEXT: .byte 0 // 0x0 |
| ; CHECK-LABEL: reverse_v16i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: adrp x8, .LCPI0_0 |
| ; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI0_0] |
| ; CHECK-NEXT: tbl v0.16b, { v0.16b }, v1.16b |
| ; CHECK-NEXT: ret |
| |
| %res = call <16 x i8> @llvm.experimental.vector.reverse.v16i8(<16 x i8> %a) |
| ret <16 x i8> %res |
| } |
| |
| define <8 x i16> @reverse_v8i16(<8 x i16> %a) #0 { |
| ; CHECK-LABEL: .LCPI1_0: |
| ; CHECK: .byte 14 // 0xe |
| ; CHECK-NEXT: .byte 15 // 0xf |
| ; CHECK-NEXT: .byte 12 // 0xc |
| ; CHECK-NEXT: .byte 13 // 0xd |
| ; CHECK-NEXT: .byte 10 // 0xa |
| ; CHECK-NEXT: .byte 11 // 0xb |
| ; CHECK-NEXT: .byte 8 // 0x8 |
| ; CHECK-NEXT: .byte 9 // 0x9 |
| ; CHECK-NEXT: .byte 6 // 0x6 |
| ; CHECK-NEXT: .byte 7 // 0x7 |
| ; CHECK-NEXT: .byte 4 // 0x4 |
| ; CHECK-NEXT: .byte 5 // 0x5 |
| ; CHECK-NEXT: .byte 2 // 0x2 |
| ; CHECK-NEXT: .byte 3 // 0x3 |
| ; CHECK-NEXT: .byte 0 // 0x0 |
| ; CHECK-NEXT: .byte 1 // 0x1 |
| ; CHECK-LABEL: reverse_v8i16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: adrp x8, .LCPI1_0 |
| ; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI1_0] |
| ; CHECK-NEXT: tbl v0.16b, { v0.16b }, v1.16b |
| ; CHECK-NEXT: ret |
| |
| %res = call <8 x i16> @llvm.experimental.vector.reverse.v8i16(<8 x i16> %a) |
| ret <8 x i16> %res |
| } |
| |
| define <4 x i32> @reverse_v4i32(<4 x i32> %a) #0 { |
| ; CHECK-LABEL: reverse_v4i32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: rev64 v0.4s, v0.4s |
| ; CHECK-NEXT: ext v0.16b, v0.16b, v0.16b, #8 |
| ; CHECK-NEXT: ret |
| |
| %res = call <4 x i32> @llvm.experimental.vector.reverse.v4i32(<4 x i32> %a) |
| ret <4 x i32> %res |
| } |
| |
| define <2 x i64> @reverse_v2i64(<2 x i64> %a) #0 { |
| ; CHECK-LABEL: reverse_v2i64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ext v0.16b, v0.16b, v0.16b, #8 |
| ; CHECK-NEXT: ret |
| |
| %res = call <2 x i64> @llvm.experimental.vector.reverse.v2i64(<2 x i64> %a) |
| ret <2 x i64> %res |
| } |
| |
| define <8 x half> @reverse_v8f16(<8 x half> %a) #0 { |
| ; CHECK-LABEL: .LCPI4_0: |
| ; CHECK: .byte 14 // 0xe |
| ; CHECK-NEXT: .byte 15 // 0xf |
| ; CHECK-NEXT: .byte 12 // 0xc |
| ; CHECK-NEXT: .byte 13 // 0xd |
| ; CHECK-NEXT: .byte 10 // 0xa |
| ; CHECK-NEXT: .byte 11 // 0xb |
| ; CHECK-NEXT: .byte 8 // 0x8 |
| ; CHECK-NEXT: .byte 9 // 0x9 |
| ; CHECK-NEXT: .byte 6 // 0x6 |
| ; CHECK-NEXT: .byte 7 // 0x7 |
| ; CHECK-NEXT: .byte 4 // 0x4 |
| ; CHECK-NEXT: .byte 5 // 0x5 |
| ; CHECK-NEXT: .byte 2 // 0x2 |
| ; CHECK-NEXT: .byte 3 // 0x3 |
| ; CHECK-NEXT: .byte 0 // 0x0 |
| ; CHECK-NEXT: .byte 1 // 0x1 |
| ; CHECK-LABEL: reverse_v8f16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: adrp x8, .LCPI4_0 |
| ; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI4_0] |
| ; CHECK-NEXT: tbl v0.16b, { v0.16b }, v1.16b |
| ; CHECK-NEXT: ret |
| |
| %res = call <8 x half> @llvm.experimental.vector.reverse.v8f16(<8 x half> %a) |
| ret <8 x half> %res |
| } |
| |
| define <4 x float> @reverse_v4f32(<4 x float> %a) #0 { |
| ; CHECK-LABEL: reverse_v4f32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: rev64 v0.4s, v0.4s |
| ; CHECK-NEXT: ext v0.16b, v0.16b, v0.16b, #8 |
| ; CHECK-NEXT: ret |
| |
| %res = call <4 x float> @llvm.experimental.vector.reverse.v4f32(<4 x float> %a) |
| ret <4 x float> %res |
| } |
| |
| define <2 x double> @reverse_v2f64(<2 x double> %a) #0 { |
| ; CHECK-LABEL: reverse_v2f64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ext v0.16b, v0.16b, v0.16b, #8 |
| ; CHECK-NEXT: ret |
| |
| %res = call <2 x double> @llvm.experimental.vector.reverse.v2f64(<2 x double> %a) |
| ret <2 x double> %res |
| } |
| |
| ; Verify promote type legalisation works as expected. |
| define <2 x i8> @reverse_v2i8(<2 x i8> %a) #0 { |
| ; CHECK-LABEL: reverse_v2i8: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: rev64 v0.2s, v0.2s |
| ; CHECK-NEXT: ret |
| |
| %res = call <2 x i8> @llvm.experimental.vector.reverse.v2i8(<2 x i8> %a) |
| ret <2 x i8> %res |
| } |
| |
| ; Verify splitvec type legalisation works as expected. |
| define <8 x i32> @reverse_v8i32(<8 x i32> %a) #0 { |
| ; CHECK-LABEL: reverse_v8i32: |
| ; CHECK-SELDAG: // %bb.0: |
| ; CHECK-SELDAG-NEXT: rev64 v1.4s, v1.4s |
| ; CHECK-SELDAG-NEXT: rev64 v2.4s, v0.4s |
| ; CHECK-SELDAG-NEXT: ext v0.16b, v1.16b, v1.16b, #8 |
| ; CHECK-SELDAG-NEXT: ext v1.16b, v2.16b, v2.16b, #8 |
| ; CHECK-SELDAG-NEXT: ret |
| ; CHECK-FASTISEL: // %bb.0: |
| ; CHECK-FASTISEL-NEXT: sub sp, sp, #16 |
| ; CHECK-FASTISEL-NEXT: str q1, [sp] |
| ; CHECK-FASTISEL-NEXT: mov v1.16b, v0.16b |
| ; CHECK-FASTISEL-NEXT: ldr q0, [sp] |
| ; CHECK-FASTISEL-NEXT: rev64 v0.4s, v0.4s |
| ; CHECK-FASTISEL-NEXT: ext v0.16b, v0.16b, v0.16b, #8 |
| ; CHECK-FASTISEL-NEXT: rev64 v1.4s, v1.4s |
| ; CHECK-FASTISEL-NEXT: ext v1.16b, v1.16b, v1.16b, #8 |
| ; CHECK-FASTISEL-NEXT: add sp, sp, #16 |
| ; CHECK-FASTISEL-NEXT: ret |
| |
| %res = call <8 x i32> @llvm.experimental.vector.reverse.v8i32(<8 x i32> %a) |
| ret <8 x i32> %res |
| } |
| |
| ; Verify splitvec type legalisation works as expected. |
| define <16 x float> @reverse_v16f32(<16 x float> %a) #0 { |
| ; CHECK-LABEL: reverse_v16f32: |
| ; CHECK-SELDAG: // %bb.0: |
| ; CHECK-SELDAG-NEXT: rev64 v3.4s, v3.4s |
| ; CHECK-SELDAG-NEXT: rev64 v2.4s, v2.4s |
| ; CHECK-SELDAG-NEXT: rev64 v4.4s, v1.4s |
| ; CHECK-SELDAG-NEXT: rev64 v5.4s, v0.4s |
| ; CHECK-SELDAG-NEXT: ext v0.16b, v3.16b, v3.16b, #8 |
| ; CHECK-SELDAG-NEXT: ext v1.16b, v2.16b, v2.16b, #8 |
| ; CHECK-SELDAG-NEXT: ext v2.16b, v4.16b, v4.16b, #8 |
| ; CHECK-SELDAG-NEXT: ext v3.16b, v5.16b, v5.16b, #8 |
| ; CHECK-SELDAG-NEXT: ret |
| ; CHECK-FASTISEL: // %bb.0: |
| ; CHECK-FASTISEL-NEXT: sub sp, sp, #32 |
| ; CHECK-FASTISEL-NEXT: str q3, [sp, #16] |
| ; CHECK-FASTISEL-NEXT: str q2, [sp] |
| ; CHECK-FASTISEL-NEXT: mov v2.16b, v1.16b |
| ; CHECK-FASTISEL-NEXT: ldr q1, [sp] |
| ; CHECK-FASTISEL-NEXT: mov v3.16b, v0.16b |
| ; CHECK-FASTISEL-NEXT: ldr q0, [sp, #16] |
| ; CHECK-FASTISEL-NEXT: rev64 v0.4s, v0.4s |
| ; CHECK-FASTISEL-NEXT: ext v0.16b, v0.16b, v0.16b, #8 |
| ; CHECK-FASTISEL-NEXT: rev64 v1.4s, v1.4s |
| ; CHECK-FASTISEL-NEXT: ext v1.16b, v1.16b, v1.16b, #8 |
| ; CHECK-FASTISEL-NEXT: rev64 v2.4s, v2.4s |
| ; CHECK-FASTISEL-NEXT: ext v2.16b, v2.16b, v2.16b, #8 |
| ; CHECK-FASTISEL-NEXT: rev64 v3.4s, v3.4s |
| ; CHECK-FASTISEL-NEXT: ext v3.16b, v3.16b, v3.16b, #8 |
| ; CHECK-FASTISEL-NEXT: add sp, sp, #32 |
| ; CHECK-FASTISEL-NEXT: ret |
| |
| %res = call <16 x float> @llvm.experimental.vector.reverse.v16f32(<16 x float> %a) |
| ret <16 x float> %res |
| } |
| |
| |
| declare <2 x i8> @llvm.experimental.vector.reverse.v2i8(<2 x i8>) |
| declare <16 x i8> @llvm.experimental.vector.reverse.v16i8(<16 x i8>) |
| declare <8 x i16> @llvm.experimental.vector.reverse.v8i16(<8 x i16>) |
| declare <4 x i32> @llvm.experimental.vector.reverse.v4i32(<4 x i32>) |
| declare <8 x i32> @llvm.experimental.vector.reverse.v8i32(<8 x i32>) |
| declare <2 x i64> @llvm.experimental.vector.reverse.v2i64(<2 x i64>) |
| declare <8 x half> @llvm.experimental.vector.reverse.v8f16(<8 x half>) |
| declare <4 x float> @llvm.experimental.vector.reverse.v4f32(<4 x float>) |
| declare <16 x float> @llvm.experimental.vector.reverse.v16f32(<16 x float>) |
| declare <2 x double> @llvm.experimental.vector.reverse.v2f64(<2 x double>) |
| |
| attributes #0 = { nounwind "target-features"="+neon" } |