diff options
Diffstat (limited to 'llvm/test/CodeGen')
5 files changed, 704 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AArch64/vecreduce-add-legalization.ll b/llvm/test/CodeGen/AArch64/vecreduce-add-legalization.ll new file mode 100644 index 00000000000..eb4bd8c5c7b --- /dev/null +++ b/llvm/test/CodeGen/AArch64/vecreduce-add-legalization.ll @@ -0,0 +1,169 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK + +declare i1 @llvm.experimental.vector.reduce.add.i1.v1i1(<1 x i1> %a) +declare i8 @llvm.experimental.vector.reduce.add.i8.v1i8(<1 x i8> %a) +declare i16 @llvm.experimental.vector.reduce.add.i16.v1i16(<1 x i16> %a) +declare i24 @llvm.experimental.vector.reduce.add.i24.v1i24(<1 x i24> %a) +declare i32 @llvm.experimental.vector.reduce.add.i32.v1i32(<1 x i32> %a) +declare i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> %a) +declare i128 @llvm.experimental.vector.reduce.add.i128.v1i128(<1 x i128> %a) + +declare i8 @llvm.experimental.vector.reduce.add.i8.v3i8(<3 x i8> %a) +declare i8 @llvm.experimental.vector.reduce.add.i8.v9i8(<9 x i8> %a) +declare i32 @llvm.experimental.vector.reduce.add.i32.v3i32(<3 x i32> %a) +declare i1 @llvm.experimental.vector.reduce.add.i1.v4i1(<4 x i1> %a) +declare i24 @llvm.experimental.vector.reduce.add.i24.v4i24(<4 x i24> %a) +declare i128 @llvm.experimental.vector.reduce.add.i128.v2i128(<2 x i128> %a) +declare i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> %a) + +define i1 @test_v1i1(<1 x i1> %a) nounwind { +; CHECK-LABEL: test_v1i1: +; CHECK: // %bb.0: +; CHECK-NEXT: and w0, w0, #0x1 +; CHECK-NEXT: ret + %b = call i1 @llvm.experimental.vector.reduce.add.i1.v1i1(<1 x i1> %a) + ret i1 %b +} + +define i8 @test_v1i8(<1 x i8> %a) nounwind { +; CHECK-LABEL: test_v1i8: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w0, v0.b[0] +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.add.i8.v1i8(<1 x i8> %a) + ret i8 %b +} + +define i16 @test_v1i16(<1 x i16> %a) nounwind { +; CHECK-LABEL: test_v1i16: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w0, v0.h[0] +; CHECK-NEXT: ret + %b = call i16 @llvm.experimental.vector.reduce.add.i16.v1i16(<1 x i16> %a) + ret i16 %b +} + +define i24 @test_v1i24(<1 x i24> %a) nounwind { +; CHECK-LABEL: test_v1i24: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call i24 @llvm.experimental.vector.reduce.add.i24.v1i24(<1 x i24> %a) + ret i24 %b +} + +define i32 @test_v1i32(<1 x i32> %a) nounwind { +; CHECK-LABEL: test_v1i32: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.add.i32.v1i32(<1 x i32> %a) + ret i32 %b +} + +define i64 @test_v1i64(<1 x i64> %a) nounwind { +; CHECK-LABEL: test_v1i64: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: fmov x0, d0 +; CHECK-NEXT: ret + %b = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> %a) + ret i64 %b +} + +define i128 @test_v1i128(<1 x i128> %a) nounwind { +; CHECK-LABEL: test_v1i128: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call i128 @llvm.experimental.vector.reduce.add.i128.v1i128(<1 x i128> %a) + ret i128 %b +} + +define i8 @test_v3i8(<3 x i8> %a) nounwind { +; CHECK-LABEL: test_v3i8: +; CHECK: // %bb.0: +; CHECK-NEXT: movi d0, #0000000000000000 +; CHECK-NEXT: mov v0.h[0], w0 +; CHECK-NEXT: mov v0.h[1], w1 +; CHECK-NEXT: mov v0.h[2], w2 +; CHECK-NEXT: addv h0, v0.4h +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.add.i8.v3i8(<3 x i8> %a) + ret i8 %b +} + +define i8 @test_v9i8(<9 x i8> %a) nounwind { +; CHECK-LABEL: test_v9i8: +; CHECK: // %bb.0: +; CHECK-NEXT: mov v0.b[9], wzr +; CHECK-NEXT: mov v0.b[10], wzr +; CHECK-NEXT: mov v0.b[11], wzr +; CHECK-NEXT: mov v0.b[12], wzr +; CHECK-NEXT: mov v0.b[13], wzr +; CHECK-NEXT: mov v0.b[14], wzr +; CHECK-NEXT: mov v0.b[15], wzr +; CHECK-NEXT: addv b0, v0.16b +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.add.i8.v9i8(<9 x i8> %a) + ret i8 %b +} + +define i32 @test_v3i32(<3 x i32> %a) nounwind { +; CHECK-LABEL: test_v3i32: +; CHECK: // %bb.0: +; CHECK-NEXT: mov v0.s[3], wzr +; CHECK-NEXT: addv s0, v0.4s +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.add.i32.v3i32(<3 x i32> %a) + ret i32 %b +} + +define i1 @test_v4i1(<4 x i1> %a) nounwind { +; CHECK-LABEL: test_v4i1: +; CHECK: // %bb.0: +; CHECK-NEXT: addv h0, v0.4h +; CHECK-NEXT: fmov w8, s0 +; CHECK-NEXT: and w0, w8, #0x1 +; CHECK-NEXT: ret + %b = call i1 @llvm.experimental.vector.reduce.add.i1.v4i1(<4 x i1> %a) + ret i1 %b +} + +define i24 @test_v4i24(<4 x i24> %a) nounwind { +; CHECK-LABEL: test_v4i24: +; CHECK: // %bb.0: +; CHECK-NEXT: addv s0, v0.4s +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i24 @llvm.experimental.vector.reduce.add.i24.v4i24(<4 x i24> %a) + ret i24 %b +} + +define i128 @test_v2i128(<2 x i128> %a) nounwind { +; CHECK-LABEL: test_v2i128: +; CHECK: // %bb.0: +; CHECK-NEXT: adds x0, x0, x2 +; CHECK-NEXT: adcs x1, x1, x3 +; CHECK-NEXT: ret + %b = call i128 @llvm.experimental.vector.reduce.add.i128.v2i128(<2 x i128> %a) + ret i128 %b +} + +define i32 @test_v16i32(<16 x i32> %a) nounwind { +; CHECK-LABEL: test_v16i32: +; CHECK: // %bb.0: +; CHECK-NEXT: add v1.4s, v1.4s, v3.4s +; CHECK-NEXT: add v0.4s, v0.4s, v2.4s +; CHECK-NEXT: add v0.4s, v0.4s, v1.4s +; CHECK-NEXT: addv s0, v0.4s +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> %a) + ret i32 %b +} diff --git a/llvm/test/CodeGen/AArch64/vecreduce-and-legalization.ll b/llvm/test/CodeGen/AArch64/vecreduce-and-legalization.ll new file mode 100644 index 00000000000..78032521a85 --- /dev/null +++ b/llvm/test/CodeGen/AArch64/vecreduce-and-legalization.ll @@ -0,0 +1,198 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK + +declare i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> %a) +declare i8 @llvm.experimental.vector.reduce.and.i8.v1i8(<1 x i8> %a) +declare i16 @llvm.experimental.vector.reduce.and.i16.v1i16(<1 x i16> %a) +declare i24 @llvm.experimental.vector.reduce.and.i24.v1i24(<1 x i24> %a) +declare i32 @llvm.experimental.vector.reduce.and.i32.v1i32(<1 x i32> %a) +declare i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> %a) +declare i128 @llvm.experimental.vector.reduce.and.i128.v1i128(<1 x i128> %a) + +declare i8 @llvm.experimental.vector.reduce.and.i8.v3i8(<3 x i8> %a) +declare i8 @llvm.experimental.vector.reduce.and.i8.v9i8(<9 x i8> %a) +declare i32 @llvm.experimental.vector.reduce.and.i32.v3i32(<3 x i32> %a) +declare i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> %a) +declare i24 @llvm.experimental.vector.reduce.and.i24.v4i24(<4 x i24> %a) +declare i128 @llvm.experimental.vector.reduce.and.i128.v2i128(<2 x i128> %a) +declare i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> %a) + +define i1 @test_v1i1(<1 x i1> %a) nounwind { +; CHECK-LABEL: test_v1i1: +; CHECK: // %bb.0: +; CHECK-NEXT: and w0, w0, #0x1 +; CHECK-NEXT: ret + %b = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> %a) + ret i1 %b +} + +define i8 @test_v1i8(<1 x i8> %a) nounwind { +; CHECK-LABEL: test_v1i8: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w0, v0.b[0] +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.and.i8.v1i8(<1 x i8> %a) + ret i8 %b +} + +define i16 @test_v1i16(<1 x i16> %a) nounwind { +; CHECK-LABEL: test_v1i16: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w0, v0.h[0] +; CHECK-NEXT: ret + %b = call i16 @llvm.experimental.vector.reduce.and.i16.v1i16(<1 x i16> %a) + ret i16 %b +} + +define i24 @test_v1i24(<1 x i24> %a) nounwind { +; CHECK-LABEL: test_v1i24: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call i24 @llvm.experimental.vector.reduce.and.i24.v1i24(<1 x i24> %a) + ret i24 %b +} + +define i32 @test_v1i32(<1 x i32> %a) nounwind { +; CHECK-LABEL: test_v1i32: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.and.i32.v1i32(<1 x i32> %a) + ret i32 %b +} + +define i64 @test_v1i64(<1 x i64> %a) nounwind { +; CHECK-LABEL: test_v1i64: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: fmov x0, d0 +; CHECK-NEXT: ret + %b = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> %a) + ret i64 %b +} + +define i128 @test_v1i128(<1 x i128> %a) nounwind { +; CHECK-LABEL: test_v1i128: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call i128 @llvm.experimental.vector.reduce.and.i128.v1i128(<1 x i128> %a) + ret i128 %b +} + +define i8 @test_v3i8(<3 x i8> %a) nounwind { +; CHECK-LABEL: test_v3i8: +; CHECK: // %bb.0: +; CHECK-NEXT: and w8, w0, w1 +; CHECK-NEXT: and w8, w8, w2 +; CHECK-NEXT: and w0, w8, #0xff +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.and.i8.v3i8(<3 x i8> %a) + ret i8 %b +} + +define i8 @test_v9i8(<9 x i8> %a) nounwind { +; CHECK-LABEL: test_v9i8: +; CHECK: // %bb.0: +; CHECK-NEXT: mov w8, #-1 +; CHECK-NEXT: mov v0.b[9], w8 +; CHECK-NEXT: mov v0.b[10], w8 +; CHECK-NEXT: mov v0.b[11], w8 +; CHECK-NEXT: mov v0.b[12], w8 +; CHECK-NEXT: mov v0.b[13], w8 +; CHECK-NEXT: mov v0.b[14], w8 +; CHECK-NEXT: mov v0.b[15], w8 +; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8 +; CHECK-NEXT: and v0.8b, v0.8b, v1.8b +; CHECK-NEXT: umov w8, v0.b[1] +; CHECK-NEXT: umov w9, v0.b[0] +; CHECK-NEXT: and w8, w9, w8 +; CHECK-NEXT: umov w9, v0.b[2] +; CHECK-NEXT: and w8, w8, w9 +; CHECK-NEXT: umov w9, v0.b[3] +; CHECK-NEXT: and w8, w8, w9 +; CHECK-NEXT: umov w9, v0.b[4] +; CHECK-NEXT: and w8, w8, w9 +; CHECK-NEXT: umov w9, v0.b[5] +; CHECK-NEXT: and w8, w8, w9 +; CHECK-NEXT: umov w9, v0.b[6] +; CHECK-NEXT: and w8, w8, w9 +; CHECK-NEXT: umov w9, v0.b[7] +; CHECK-NEXT: and w0, w8, w9 +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.and.i8.v9i8(<9 x i8> %a) + ret i8 %b +} + +define i32 @test_v3i32(<3 x i32> %a) nounwind { +; CHECK-LABEL: test_v3i32: +; CHECK: // %bb.0: +; CHECK-NEXT: mov w8, #-1 +; CHECK-NEXT: mov v0.s[3], w8 +; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8 +; CHECK-NEXT: and v0.8b, v0.8b, v1.8b +; CHECK-NEXT: mov w8, v0.s[1] +; CHECK-NEXT: fmov w9, s0 +; CHECK-NEXT: and w0, w9, w8 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.and.i32.v3i32(<3 x i32> %a) + ret i32 %b +} + +define i1 @test_v4i1(<4 x i1> %a) nounwind { +; CHECK-LABEL: test_v4i1: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w10, v0.h[1] +; CHECK-NEXT: umov w11, v0.h[0] +; CHECK-NEXT: umov w9, v0.h[2] +; CHECK-NEXT: and w10, w11, w10 +; CHECK-NEXT: umov w8, v0.h[3] +; CHECK-NEXT: and w9, w10, w9 +; CHECK-NEXT: and w8, w9, w8 +; CHECK-NEXT: and w0, w8, #0x1 +; CHECK-NEXT: ret + %b = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> %a) + ret i1 %b +} + +define i24 @test_v4i24(<4 x i24> %a) nounwind { +; CHECK-LABEL: test_v4i24: +; CHECK: // %bb.0: +; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8 +; CHECK-NEXT: and v0.8b, v0.8b, v1.8b +; CHECK-NEXT: mov w8, v0.s[1] +; CHECK-NEXT: fmov w9, s0 +; CHECK-NEXT: and w0, w9, w8 +; CHECK-NEXT: ret + %b = call i24 @llvm.experimental.vector.reduce.and.i24.v4i24(<4 x i24> %a) + ret i24 %b +} + +define i128 @test_v2i128(<2 x i128> %a) nounwind { +; CHECK-LABEL: test_v2i128: +; CHECK: // %bb.0: +; CHECK-NEXT: and x0, x0, x2 +; CHECK-NEXT: and x1, x1, x3 +; CHECK-NEXT: ret + %b = call i128 @llvm.experimental.vector.reduce.and.i128.v2i128(<2 x i128> %a) + ret i128 %b +} + +define i32 @test_v16i32(<16 x i32> %a) nounwind { +; CHECK-LABEL: test_v16i32: +; CHECK: // %bb.0: +; CHECK-NEXT: and v1.16b, v1.16b, v3.16b +; CHECK-NEXT: and v0.16b, v0.16b, v2.16b +; CHECK-NEXT: and v0.16b, v0.16b, v1.16b +; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8 +; CHECK-NEXT: and v0.8b, v0.8b, v1.8b +; CHECK-NEXT: mov w8, v0.s[1] +; CHECK-NEXT: fmov w9, s0 +; CHECK-NEXT: and w0, w9, w8 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> %a) + ret i32 %b +} diff --git a/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll new file mode 100644 index 00000000000..86511daadff --- /dev/null +++ b/llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll @@ -0,0 +1,83 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK + +declare half @llvm.experimental.vector.reduce.fadd.f16.v1f16(half, <1 x half>) +declare float @llvm.experimental.vector.reduce.fadd.f32.v1f32(float, <1 x float>) +declare double @llvm.experimental.vector.reduce.fadd.f64.v1f64(double, <1 x double>) +declare fp128 @llvm.experimental.vector.reduce.fadd.f128.v1f128(fp128, <1 x fp128>) + +declare float @llvm.experimental.vector.reduce.fadd.f32.v3f32(float, <3 x float>) +declare fp128 @llvm.experimental.vector.reduce.fadd.f128.v2f128(fp128, <2 x fp128>) +declare float @llvm.experimental.vector.reduce.fadd.f32.v16f32(float, <16 x float>) + +define half @test_v1f16(<1 x half> %a) nounwind { +; CHECK-LABEL: test_v1f16: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call fast nnan half @llvm.experimental.vector.reduce.fadd.f16.v1f16(half 0.0, <1 x half> %a) + ret half %b +} + +define float @test_v1f32(<1 x float> %a) nounwind { +; CHECK-LABEL: test_v1f32: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: // kill: def $s0 killed $s0 killed $q0 +; CHECK-NEXT: ret + %b = call fast nnan float @llvm.experimental.vector.reduce.fadd.f32.v1f32(float 0.0, <1 x float> %a) + ret float %b +} + +define double @test_v1f64(<1 x double> %a) nounwind { +; CHECK-LABEL: test_v1f64: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call fast nnan double @llvm.experimental.vector.reduce.fadd.f64.v1f64(double 0.0, <1 x double> %a) + ret double %b +} + +define fp128 @test_v1f128(<1 x fp128> %a) nounwind { +; CHECK-LABEL: test_v1f128: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call fast nnan fp128 @llvm.experimental.vector.reduce.fadd.f128.v1f128(fp128 zeroinitializer, <1 x fp128> %a) + ret fp128 %b +} + +define float @test_v3f32(<3 x float> %a) nounwind { +; CHECK-LABEL: test_v3f32: +; CHECK: // %bb.0: +; CHECK-NEXT: fmov s1, wzr +; CHECK-NEXT: mov v0.s[3], v1.s[0] +; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8 +; CHECK-NEXT: fadd v0.2s, v0.2s, v1.2s +; CHECK-NEXT: faddp s0, v0.2s +; CHECK-NEXT: ret + %b = call fast nnan float @llvm.experimental.vector.reduce.fadd.f32.v3f32(float 0.0, <3 x float> %a) + ret float %b +} + +define fp128 @test_v2f128(<2 x fp128> %a) nounwind { +; CHECK-LABEL: test_v2f128: +; CHECK: // %bb.0: +; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: bl __addtf3 +; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret + %b = call fast nnan fp128 @llvm.experimental.vector.reduce.fadd.f128.v2f128(fp128 zeroinitializer, <2 x fp128> %a) + ret fp128 %b +} + +define float @test_v16f32(<16 x float> %a) nounwind { +; CHECK-LABEL: test_v16f32: +; CHECK: // %bb.0: +; CHECK-NEXT: fadd v1.4s, v1.4s, v3.4s +; CHECK-NEXT: fadd v0.4s, v0.4s, v2.4s +; CHECK-NEXT: fadd v0.4s, v0.4s, v1.4s +; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8 +; CHECK-NEXT: fadd v0.2s, v0.2s, v1.2s +; CHECK-NEXT: faddp s0, v0.2s +; CHECK-NEXT: ret + %b = call fast nnan float @llvm.experimental.vector.reduce.fadd.f32.v16f32(float 0.0, <16 x float> %a) + ret float %b +} diff --git a/llvm/test/CodeGen/AArch64/vecreduce-fmax-legalization.ll b/llvm/test/CodeGen/AArch64/vecreduce-fmax-legalization.ll new file mode 100644 index 00000000000..44260d53632 --- /dev/null +++ b/llvm/test/CodeGen/AArch64/vecreduce-fmax-legalization.ll @@ -0,0 +1,77 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK + +declare half @llvm.experimental.vector.reduce.fmax.f16.v1f16(<1 x half> %a) +declare float @llvm.experimental.vector.reduce.fmax.f32.v1f32(<1 x float> %a) +declare double @llvm.experimental.vector.reduce.fmax.f64.v1f64(<1 x double> %a) +declare fp128 @llvm.experimental.vector.reduce.fmax.f128.v1f128(<1 x fp128> %a) + +declare float @llvm.experimental.vector.reduce.fmax.f32.v3f32(<3 x float> %a) +declare fp128 @llvm.experimental.vector.reduce.fmax.f128.v2f128(<2 x fp128> %a) +declare float @llvm.experimental.vector.reduce.fmax.f32.v16f32(<16 x float> %a) + +define half @test_v1f16(<1 x half> %a) nounwind { +; CHECK-LABEL: test_v1f16: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call nnan half @llvm.experimental.vector.reduce.fmax.f16.v1f16(<1 x half> %a) + ret half %b +} + +define float @test_v1f32(<1 x float> %a) nounwind { +; CHECK-LABEL: test_v1f32: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: // kill: def $s0 killed $s0 killed $q0 +; CHECK-NEXT: ret + %b = call nnan float @llvm.experimental.vector.reduce.fmax.f32.v1f32(<1 x float> %a) + ret float %b +} + +define double @test_v1f64(<1 x double> %a) nounwind { +; CHECK-LABEL: test_v1f64: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call nnan double @llvm.experimental.vector.reduce.fmax.f64.v1f64(<1 x double> %a) + ret double %b +} + +define fp128 @test_v1f128(<1 x fp128> %a) nounwind { +; CHECK-LABEL: test_v1f128: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call nnan fp128 @llvm.experimental.vector.reduce.fmax.f128.v1f128(<1 x fp128> %a) + ret fp128 %b +} + +define float @test_v3f32(<3 x float> %a) nounwind { +; CHECK-LABEL: test_v3f32: +; CHECK: // %bb.0: +; CHECK-NEXT: orr w8, wzr, #0x7f800000 +; CHECK-NEXT: fmov s1, w8 +; CHECK-NEXT: mov v0.s[3], v1.s[0] +; CHECK-NEXT: fmaxnmv s0, v0.4s +; CHECK-NEXT: ret + %b = call nnan float @llvm.experimental.vector.reduce.fmax.f32.v3f32(<3 x float> %a) + ret float %b +} + +define fp128 @test_v2f128(<2 x fp128> %a) nounwind { +; CHECK-LABEL: test_v2f128: +; CHECK: // %bb.0: +; CHECK-NEXT: b fmaxl + %b = call nnan fp128 @llvm.experimental.vector.reduce.fmax.f128.v2f128(<2 x fp128> %a) + ret fp128 %b +} + +define float @test_v16f32(<16 x float> %a) nounwind { +; CHECK-LABEL: test_v16f32: +; CHECK: // %bb.0: +; CHECK-NEXT: fmaxnm v1.4s, v1.4s, v3.4s +; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v2.4s +; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v1.4s +; CHECK-NEXT: fmaxnmv s0, v0.4s +; CHECK-NEXT: ret + %b = call nnan float @llvm.experimental.vector.reduce.fmax.f32.v16f32(<16 x float> %a) + ret float %b +} diff --git a/llvm/test/CodeGen/AArch64/vecreduce-umax-legalization.ll b/llvm/test/CodeGen/AArch64/vecreduce-umax-legalization.ll new file mode 100644 index 00000000000..eff97260ea3 --- /dev/null +++ b/llvm/test/CodeGen/AArch64/vecreduce-umax-legalization.ll @@ -0,0 +1,177 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK + +declare i1 @llvm.experimental.vector.reduce.umax.i1.v1i1(<1 x i1> %a) +declare i8 @llvm.experimental.vector.reduce.umax.i8.v1i8(<1 x i8> %a) +declare i16 @llvm.experimental.vector.reduce.umax.i16.v1i16(<1 x i16> %a) +declare i24 @llvm.experimental.vector.reduce.umax.i24.v1i24(<1 x i24> %a) +declare i32 @llvm.experimental.vector.reduce.umax.i32.v1i32(<1 x i32> %a) +declare i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> %a) +declare i128 @llvm.experimental.vector.reduce.umax.i128.v1i128(<1 x i128> %a) + +declare i8 @llvm.experimental.vector.reduce.umax.i8.v3i8(<3 x i8> %a) +declare i8 @llvm.experimental.vector.reduce.umax.i8.v9i8(<9 x i8> %a) +declare i32 @llvm.experimental.vector.reduce.umax.i32.v3i32(<3 x i32> %a) +declare i1 @llvm.experimental.vector.reduce.umax.i1.v4i1(<4 x i1> %a) +declare i24 @llvm.experimental.vector.reduce.umax.i24.v4i24(<4 x i24> %a) +declare i128 @llvm.experimental.vector.reduce.umax.i128.v2i128(<2 x i128> %a) +declare i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> %a) + +define i1 @test_v1i1(<1 x i1> %a) nounwind { +; CHECK-LABEL: test_v1i1: +; CHECK: // %bb.0: +; CHECK-NEXT: and w0, w0, #0x1 +; CHECK-NEXT: ret + %b = call i1 @llvm.experimental.vector.reduce.umax.i1.v1i1(<1 x i1> %a) + ret i1 %b +} + +define i8 @test_v1i8(<1 x i8> %a) nounwind { +; CHECK-LABEL: test_v1i8: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w0, v0.b[0] +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.umax.i8.v1i8(<1 x i8> %a) + ret i8 %b +} + +define i16 @test_v1i16(<1 x i16> %a) nounwind { +; CHECK-LABEL: test_v1i16: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w0, v0.h[0] +; CHECK-NEXT: ret + %b = call i16 @llvm.experimental.vector.reduce.umax.i16.v1i16(<1 x i16> %a) + ret i16 %b +} + +define i24 @test_v1i24(<1 x i24> %a) nounwind { +; CHECK-LABEL: test_v1i24: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call i24 @llvm.experimental.vector.reduce.umax.i24.v1i24(<1 x i24> %a) + ret i24 %b +} + +define i32 @test_v1i32(<1 x i32> %a) nounwind { +; CHECK-LABEL: test_v1i32: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.umax.i32.v1i32(<1 x i32> %a) + ret i32 %b +} + +define i64 @test_v1i64(<1 x i64> %a) nounwind { +; CHECK-LABEL: test_v1i64: +; CHECK: // %bb.0: +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: fmov x0, d0 +; CHECK-NEXT: ret + %b = call i64 @llvm.experimental.vector.reduce.umax.i64.v1i64(<1 x i64> %a) + ret i64 %b +} + +define i128 @test_v1i128(<1 x i128> %a) nounwind { +; CHECK-LABEL: test_v1i128: +; CHECK: // %bb.0: +; CHECK-NEXT: ret + %b = call i128 @llvm.experimental.vector.reduce.umax.i128.v1i128(<1 x i128> %a) + ret i128 %b +} + +define i8 @test_v3i8(<3 x i8> %a) nounwind { +; CHECK-LABEL: test_v3i8: +; CHECK: // %bb.0: +; CHECK-NEXT: movi d0, #0000000000000000 +; CHECK-NEXT: mov v0.h[0], w0 +; CHECK-NEXT: mov v0.h[1], w1 +; CHECK-NEXT: mov v0.h[2], w2 +; CHECK-NEXT: bic v0.4h, #255, lsl #8 +; CHECK-NEXT: umaxv h0, v0.4h +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.umax.i8.v3i8(<3 x i8> %a) + ret i8 %b +} + +define i8 @test_v9i8(<9 x i8> %a) nounwind { +; CHECK-LABEL: test_v9i8: +; CHECK: // %bb.0: +; CHECK-NEXT: mov v0.b[9], wzr +; CHECK-NEXT: mov v0.b[10], wzr +; CHECK-NEXT: mov v0.b[11], wzr +; CHECK-NEXT: mov v0.b[12], wzr +; CHECK-NEXT: mov v0.b[13], wzr +; CHECK-NEXT: mov v0.b[14], wzr +; CHECK-NEXT: mov v0.b[15], wzr +; CHECK-NEXT: umaxv b0, v0.16b +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i8 @llvm.experimental.vector.reduce.umax.i8.v9i8(<9 x i8> %a) + ret i8 %b +} + +define i32 @test_v3i32(<3 x i32> %a) nounwind { +; CHECK-LABEL: test_v3i32: +; CHECK: // %bb.0: +; CHECK-NEXT: mov v0.s[3], wzr +; CHECK-NEXT: umaxv s0, v0.4s +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.umax.i32.v3i32(<3 x i32> %a) + ret i32 %b +} + +define i1 @test_v4i1(<4 x i1> %a) nounwind { +; CHECK-LABEL: test_v4i1: +; CHECK: // %bb.0: +; CHECK-NEXT: movi v1.4h, #1 +; CHECK-NEXT: and v0.8b, v0.8b, v1.8b +; CHECK-NEXT: umaxv h0, v0.4h +; CHECK-NEXT: fmov w8, s0 +; CHECK-NEXT: and w0, w8, #0x1 +; CHECK-NEXT: ret + %b = call i1 @llvm.experimental.vector.reduce.umax.i1.v4i1(<4 x i1> %a) + ret i1 %b +} + +define i24 @test_v4i24(<4 x i24> %a) nounwind { +; CHECK-LABEL: test_v4i24: +; CHECK: // %bb.0: +; CHECK-NEXT: bic v0.4s, #255, lsl #24 +; CHECK-NEXT: umaxv s0, v0.4s +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i24 @llvm.experimental.vector.reduce.umax.i24.v4i24(<4 x i24> %a) + ret i24 %b +} + +define i128 @test_v2i128(<2 x i128> %a) nounwind { +; CHECK-LABEL: test_v2i128: +; CHECK: // %bb.0: +; CHECK-NEXT: cmp x0, x2 +; CHECK-NEXT: csel x8, x0, x2, hi +; CHECK-NEXT: cmp x1, x3 +; CHECK-NEXT: csel x9, x0, x2, hi +; CHECK-NEXT: csel x0, x8, x9, eq +; CHECK-NEXT: csel x1, x1, x3, hi +; CHECK-NEXT: ret + %b = call i128 @llvm.experimental.vector.reduce.umax.i128.v2i128(<2 x i128> %a) + ret i128 %b +} + +define i32 @test_v16i32(<16 x i32> %a) nounwind { +; CHECK-LABEL: test_v16i32: +; CHECK: // %bb.0: +; CHECK-NEXT: umax v1.4s, v1.4s, v3.4s +; CHECK-NEXT: umax v0.4s, v0.4s, v2.4s +; CHECK-NEXT: umax v0.4s, v0.4s, v1.4s +; CHECK-NEXT: umaxv s0, v0.4s +; CHECK-NEXT: fmov w0, s0 +; CHECK-NEXT: ret + %b = call i32 @llvm.experimental.vector.reduce.umax.i32.v16i32(<16 x i32> %a) + ret i32 %b +} |
