| ; 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 --check-prefix=CHECK-NOFP --check-prefix=CHECK-NOFP-SD |
| ; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon,+fullfp16 | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP --check-prefix=CHECK-FP-SD |
| ; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon -global-isel -global-isel-abort=2 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-NOFP --check-prefix=CHECK-NOFP-GI |
| ; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon,+fullfp16 -global-isel -global-isel-abort=2 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP --check-prefix=CHECK-FP-GI |
| |
| ; GlobalISel has no legalizer rules for G_VECREDUCE_F{MAX,MIN}IMUMNUM yet, so |
| ; every function below falls back to SelectionDAG. |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v1f16 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v1f32 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v1f64 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v1f128 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v4f16 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v8f16 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v16f16 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v2f32 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v4f32 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v8f32 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v16f32 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v2f64 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v4f64 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v11f16 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v3f32 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v3f32_ninf |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v2f128 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v7f32 |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v7f32_nnan |
| ; CHECK-NOFP-GI: warning: Instruction selection used fallback path for test_v7f32_nnan_ninf |
| ; |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v1f16 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v1f32 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v1f64 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v1f128 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v4f16 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v8f16 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v16f16 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v2f32 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v4f32 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v8f32 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v16f32 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v2f64 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v4f64 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v11f16 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v3f32 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v3f32_ninf |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v2f128 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v7f32 |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v7f32_nnan |
| ; CHECK-FP-GI: warning: Instruction selection used fallback path for test_v7f32_nnan_ninf |
| ; |
| |
| define half @test_v1f16(<1 x half> %a) nounwind { |
| ; CHECK-LABEL: test_v1f16: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: ret |
| %b = call half @llvm.vector.reduce.fmaximumnum.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 float @llvm.vector.reduce.fmaximumnum.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 double @llvm.vector.reduce.fmaximumnum.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 fp128 @llvm.vector.reduce.fmaximumnum.v1f128(<1 x fp128> %a) |
| ret fp128 %b |
| } |
| |
| define half @test_v4f16(<4 x half> %a) nounwind { |
| ; CHECK-NOFP-LABEL: test_v4f16: |
| ; CHECK-NOFP: // %bb.0: |
| ; CHECK-NOFP-NEXT: // kill: def $d0 killed $d0 def $q0 |
| ; CHECK-NOFP-NEXT: mov h1, v0.h[1] |
| ; CHECK-NOFP-NEXT: fcvt s2, h0 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s2, s1 |
| ; CHECK-NOFP-NEXT: mov h2, v0.h[2] |
| ; CHECK-NOFP-NEXT: mov h0, v0.h[3] |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: ret |
| ; |
| ; CHECK-FP-LABEL: test_v4f16: |
| ; CHECK-FP: // %bb.0: |
| ; CHECK-FP-NEXT: // kill: def $d0 killed $d0 def $q0 |
| ; CHECK-FP-NEXT: mov h1, v0.h[1] |
| ; CHECK-FP-NEXT: fminnm h2, h0, h0 |
| ; CHECK-FP-NEXT: mov h3, v0.h[2] |
| ; CHECK-FP-NEXT: mov h0, v0.h[3] |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fminnm h0, h0, h0 |
| ; CHECK-FP-NEXT: fmaxnm h1, h2, h1 |
| ; CHECK-FP-NEXT: fminnm h2, h3, h3 |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h0, h1, h0 |
| ; CHECK-FP-NEXT: ret |
| %b = call half @llvm.vector.reduce.fmaximumnum.v4f16(<4 x half> %a) |
| ret half %b |
| } |
| |
| define half @test_v8f16(<8 x half> %a) nounwind { |
| ; CHECK-NOFP-LABEL: test_v8f16: |
| ; CHECK-NOFP: // %bb.0: |
| ; CHECK-NOFP-NEXT: mov h1, v0.h[1] |
| ; CHECK-NOFP-NEXT: fcvt s2, h0 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s2, s1 |
| ; CHECK-NOFP-NEXT: mov h2, v0.h[2] |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NOFP-NEXT: mov h2, v0.h[3] |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NOFP-NEXT: mov h2, v0.h[4] |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NOFP-NEXT: mov h2, v0.h[5] |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NOFP-NEXT: mov h2, v0.h[6] |
| ; CHECK-NOFP-NEXT: mov h0, v0.h[7] |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: ret |
| ; |
| ; CHECK-FP-LABEL: test_v8f16: |
| ; CHECK-FP: // %bb.0: |
| ; CHECK-FP-NEXT: mov h1, v0.h[1] |
| ; CHECK-FP-NEXT: fminnm h2, h0, h0 |
| ; CHECK-FP-NEXT: mov h3, v0.h[2] |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h2, h1 |
| ; CHECK-FP-NEXT: fminnm h2, h3, h3 |
| ; CHECK-FP-NEXT: mov h3, v0.h[3] |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fminnm h2, h3, h3 |
| ; CHECK-FP-NEXT: mov h3, v0.h[4] |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fminnm h2, h3, h3 |
| ; CHECK-FP-NEXT: mov h3, v0.h[5] |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fminnm h2, h3, h3 |
| ; CHECK-FP-NEXT: mov h3, v0.h[6] |
| ; CHECK-FP-NEXT: mov h0, v0.h[7] |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fminnm h0, h0, h0 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fminnm h2, h3, h3 |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fminnm h1, h1, h1 |
| ; CHECK-FP-NEXT: fmaxnm h0, h1, h0 |
| ; CHECK-FP-NEXT: ret |
| %b = call half @llvm.vector.reduce.fmaximumnum.v8f16(<8 x half> %a) |
| ret half %b |
| } |
| |
| define half @test_v16f16(<16 x half> %a) nounwind { |
| ; CHECK-NOFP-LABEL: test_v16f16: |
| ; CHECK-NOFP: // %bb.0: |
| ; CHECK-NOFP-NEXT: mov h2, v1.h[1] |
| ; CHECK-NOFP-NEXT: mov h3, v0.h[1] |
| ; CHECK-NOFP-NEXT: fcvt s4, h1 |
| ; CHECK-NOFP-NEXT: fcvt s5, h0 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s3, h3 |
| ; CHECK-NOFP-NEXT: fmaxnm s4, s5, s4 |
| ; CHECK-NOFP-NEXT: mov h5, v0.h[2] |
| ; CHECK-NOFP-NEXT: fmaxnm s2, s3, s2 |
| ; CHECK-NOFP-NEXT: mov h3, v1.h[2] |
| ; CHECK-NOFP-NEXT: fcvt h4, s4 |
| ; CHECK-NOFP-NEXT: fcvt s5, h5 |
| ; CHECK-NOFP-NEXT: fcvt h2, s2 |
| ; CHECK-NOFP-NEXT: fcvt s3, h3 |
| ; CHECK-NOFP-NEXT: fcvt s4, h4 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fmaxnm s3, s5, s3 |
| ; CHECK-NOFP-NEXT: mov h5, v0.h[3] |
| ; CHECK-NOFP-NEXT: fmaxnm s2, s4, s2 |
| ; CHECK-NOFP-NEXT: mov h4, v1.h[3] |
| ; CHECK-NOFP-NEXT: fcvt h3, s3 |
| ; CHECK-NOFP-NEXT: fcvt s5, h5 |
| ; CHECK-NOFP-NEXT: fcvt h2, s2 |
| ; CHECK-NOFP-NEXT: fcvt s4, h4 |
| ; CHECK-NOFP-NEXT: fcvt s3, h3 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fmaxnm s4, s5, s4 |
| ; CHECK-NOFP-NEXT: mov h5, v0.h[4] |
| ; CHECK-NOFP-NEXT: fmaxnm s2, s2, s3 |
| ; CHECK-NOFP-NEXT: mov h3, v1.h[4] |
| ; CHECK-NOFP-NEXT: fcvt h4, s4 |
| ; CHECK-NOFP-NEXT: fcvt s5, h5 |
| ; CHECK-NOFP-NEXT: fcvt h2, s2 |
| ; CHECK-NOFP-NEXT: fcvt s3, h3 |
| ; CHECK-NOFP-NEXT: fcvt s4, h4 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fmaxnm s3, s5, s3 |
| ; CHECK-NOFP-NEXT: mov h5, v0.h[5] |
| ; CHECK-NOFP-NEXT: fmaxnm s2, s2, s4 |
| ; CHECK-NOFP-NEXT: mov h4, v1.h[5] |
| ; CHECK-NOFP-NEXT: fcvt h3, s3 |
| ; CHECK-NOFP-NEXT: fcvt s5, h5 |
| ; CHECK-NOFP-NEXT: fcvt h2, s2 |
| ; CHECK-NOFP-NEXT: fcvt s4, h4 |
| ; CHECK-NOFP-NEXT: fcvt s3, h3 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fmaxnm s4, s5, s4 |
| ; CHECK-NOFP-NEXT: mov h5, v0.h[6] |
| ; CHECK-NOFP-NEXT: mov h0, v0.h[7] |
| ; CHECK-NOFP-NEXT: fmaxnm s2, s2, s3 |
| ; CHECK-NOFP-NEXT: fcvt h3, s4 |
| ; CHECK-NOFP-NEXT: mov h4, v1.h[6] |
| ; CHECK-NOFP-NEXT: fcvt s5, h5 |
| ; CHECK-NOFP-NEXT: mov h1, v1.h[7] |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fcvt h2, s2 |
| ; CHECK-NOFP-NEXT: fcvt s3, h3 |
| ; CHECK-NOFP-NEXT: fcvt s4, h4 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fmaxnm s2, s2, s3 |
| ; CHECK-NOFP-NEXT: fmaxnm s3, s5, s4 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt h2, s2 |
| ; CHECK-NOFP-NEXT: fcvt h3, s3 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s3, h3 |
| ; CHECK-NOFP-NEXT: fmaxnm s2, s2, s3 |
| ; CHECK-NOFP-NEXT: fcvt h1, s2 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: ret |
| ; |
| ; CHECK-FP-LABEL: test_v16f16: |
| ; CHECK-FP: // %bb.0: |
| ; CHECK-FP-NEXT: fminnm v1.8h, v1.8h, v1.8h |
| ; CHECK-FP-NEXT: fminnm v0.8h, v0.8h, v0.8h |
| ; CHECK-FP-NEXT: fmaxnm v0.8h, v0.8h, v1.8h |
| ; CHECK-FP-NEXT: mov h1, v0.h[1] |
| ; CHECK-FP-NEXT: mov h2, v0.h[2] |
| ; CHECK-FP-NEXT: fmaxnm h1, h0, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[3] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[4] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[5] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[6] |
| ; CHECK-FP-NEXT: mov h0, v0.h[7] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fmaxnm h0, h1, h0 |
| ; CHECK-FP-NEXT: ret |
| %b = call half @llvm.vector.reduce.fmaximumnum.v16f16(<16 x half> %a) |
| ret half %b |
| } |
| |
| define float @test_v2f32(<2 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v2f32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: fminnm s0, s0, s0 |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NEXT: ret |
| %b = call float @llvm.vector.reduce.fmaximumnum.v2f32(<2 x float> %a) |
| ret float %b |
| } |
| |
| define float @test_v4f32(<4 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v4f32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: fminnm s2, s0, s0 |
| ; CHECK-NEXT: mov s3, v0.s[2] |
| ; CHECK-NEXT: mov s0, v0.s[3] |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fminnm s0, s0, s0 |
| ; CHECK-NEXT: fmaxnm s1, s2, s1 |
| ; CHECK-NEXT: fminnm s2, s3, s3 |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call float @llvm.vector.reduce.fmaximumnum.v4f32(<4 x float> %a) |
| ret float %b |
| } |
| |
| define float @test_v8f32(<8 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v8f32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: fminnm v1.4s, v1.4s, v1.4s |
| ; CHECK-NEXT: fminnm v0.4s, v0.4s, v0.4s |
| ; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v1.4s |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: mov s2, v0.s[2] |
| ; CHECK-NEXT: fmaxnm s1, s0, s1 |
| ; CHECK-NEXT: mov s0, v0.s[3] |
| ; CHECK-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call float @llvm.vector.reduce.fmaximumnum.v8f32(<8 x float> %a) |
| ret float %b |
| } |
| |
| define float @test_v16f32(<16 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v16f32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: fminnm v3.4s, v3.4s, v3.4s |
| ; CHECK-NEXT: fminnm v1.4s, v1.4s, v1.4s |
| ; CHECK-NEXT: fminnm v2.4s, v2.4s, v2.4s |
| ; CHECK-NEXT: fminnm v0.4s, v0.4s, v0.4s |
| ; 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: mov s1, v0.s[1] |
| ; CHECK-NEXT: mov s2, v0.s[2] |
| ; CHECK-NEXT: fmaxnm s1, s0, s1 |
| ; CHECK-NEXT: mov s0, v0.s[3] |
| ; CHECK-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call float @llvm.vector.reduce.fmaximumnum.v16f32(<16 x float> %a) |
| ret float %b |
| } |
| |
| define double @test_v2f64(<2 x double> %a) nounwind { |
| ; CHECK-LABEL: test_v2f64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mov d1, v0.d[1] |
| ; CHECK-NEXT: fminnm d0, d0, d0 |
| ; CHECK-NEXT: fminnm d1, d1, d1 |
| ; CHECK-NEXT: fmaxnm d0, d0, d1 |
| ; CHECK-NEXT: ret |
| %b = call double @llvm.vector.reduce.fmaximumnum.v2f64(<2 x double> %a) |
| ret double %b |
| } |
| |
| define double @test_v4f64(<4 x double> %a) nounwind { |
| ; CHECK-LABEL: test_v4f64: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: fminnm v1.2d, v1.2d, v1.2d |
| ; CHECK-NEXT: fminnm v0.2d, v0.2d, v0.2d |
| ; CHECK-NEXT: fmaxnm v0.2d, v0.2d, v1.2d |
| ; CHECK-NEXT: mov d1, v0.d[1] |
| ; CHECK-NEXT: fmaxnm d0, d0, d1 |
| ; CHECK-NEXT: ret |
| %b = call double @llvm.vector.reduce.fmaximumnum.v4f64(<4 x double> %a) |
| ret double %b |
| } |
| |
| define half @test_v11f16(<11 x half> %a) nounwind { |
| ; CHECK-NOFP-LABEL: test_v11f16: |
| ; CHECK-NOFP: // %bb.0: |
| ; CHECK-NOFP-NEXT: ldr h16, [sp, #8] |
| ; CHECK-NOFP-NEXT: ldr h17, [sp] |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fcvt s2, h2 |
| ; CHECK-NOFP-NEXT: fcvt s16, h16 |
| ; CHECK-NOFP-NEXT: fcvt s17, h17 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s1, s16 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s17 |
| ; CHECK-NOFP-NEXT: ldr h16, [sp, #16] |
| ; CHECK-NOFP-NEXT: fcvt s16, h16 |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fmaxnm s1, s2, s16 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt h1, s1 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fcvt s1, h1 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fcvt s1, h3 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fcvt s1, h4 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fcvt s1, h5 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fcvt s1, h6 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fcvt s1, h7 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: fcvt s0, h0 |
| ; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1 |
| ; CHECK-NOFP-NEXT: fcvt h0, s0 |
| ; CHECK-NOFP-NEXT: ret |
| ; |
| ; CHECK-FP-LABEL: test_v11f16: |
| ; CHECK-FP: // %bb.0: |
| ; CHECK-FP-NEXT: // kill: def $h0 killed $h0 def $q0 |
| ; CHECK-FP-NEXT: // kill: def $h1 killed $h1 def $q1 |
| ; CHECK-FP-NEXT: // kill: def $h2 killed $h2 def $q2 |
| ; CHECK-FP-NEXT: // kill: def $h3 killed $h3 def $q3 |
| ; CHECK-FP-NEXT: // kill: def $h4 killed $h4 def $q4 |
| ; CHECK-FP-NEXT: // kill: def $h5 killed $h5 def $q5 |
| ; CHECK-FP-NEXT: mov x8, sp |
| ; CHECK-FP-NEXT: // kill: def $h6 killed $h6 def $q6 |
| ; CHECK-FP-NEXT: // kill: def $h7 killed $h7 def $q7 |
| ; CHECK-FP-NEXT: mov v0.h[1], v1.h[0] |
| ; CHECK-FP-NEXT: movi v1.8h, #254, lsl #8 |
| ; CHECK-FP-NEXT: mov v0.h[2], v2.h[0] |
| ; CHECK-FP-NEXT: ld1 { v1.h }[0], [x8] |
| ; CHECK-FP-NEXT: add x8, sp, #8 |
| ; CHECK-FP-NEXT: ld1 { v1.h }[1], [x8] |
| ; CHECK-FP-NEXT: add x8, sp, #16 |
| ; CHECK-FP-NEXT: mov v0.h[3], v3.h[0] |
| ; CHECK-FP-NEXT: ld1 { v1.h }[2], [x8] |
| ; CHECK-FP-NEXT: mov v0.h[4], v4.h[0] |
| ; CHECK-FP-NEXT: fminnm v1.8h, v1.8h, v1.8h |
| ; CHECK-FP-NEXT: mov v0.h[5], v5.h[0] |
| ; CHECK-FP-NEXT: mov v0.h[6], v6.h[0] |
| ; CHECK-FP-NEXT: mov v0.h[7], v7.h[0] |
| ; CHECK-FP-NEXT: fminnm v0.8h, v0.8h, v0.8h |
| ; CHECK-FP-NEXT: fmaxnm v0.8h, v0.8h, v1.8h |
| ; CHECK-FP-NEXT: mov h1, v0.h[1] |
| ; CHECK-FP-NEXT: mov h2, v0.h[2] |
| ; CHECK-FP-NEXT: fmaxnm h1, h0, h1 |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[3] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[4] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[5] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: mov h2, v0.h[6] |
| ; CHECK-FP-NEXT: mov h0, v0.h[7] |
| ; CHECK-FP-NEXT: fmaxnm h1, h1, h2 |
| ; CHECK-FP-NEXT: fmaxnm h0, h1, h0 |
| ; CHECK-FP-NEXT: ret |
| %b = call half @llvm.vector.reduce.fmaximumnum.v11f16(<11 x half> %a) |
| ret half %b |
| } |
| |
| define float @test_v3f32(<3 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v3f32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: fminnm s2, s0, s0 |
| ; CHECK-NEXT: mov s0, v0.s[2] |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fminnm s0, s0, s0 |
| ; CHECK-NEXT: fmaxnm s1, s2, s1 |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call float @llvm.vector.reduce.fmaximumnum.v3f32(<3 x float> %a) |
| ret float %b |
| } |
| |
| define float @test_v3f32_ninf(<3 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v3f32_ninf: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: fminnm s2, s0, s0 |
| ; CHECK-NEXT: mov s0, v0.s[2] |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fminnm s0, s0, s0 |
| ; CHECK-NEXT: fmaxnm s1, s2, s1 |
| ; CHECK-NEXT: fminnm s1, s1, s1 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call ninf float @llvm.vector.reduce.fmaximumnum.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: sub sp, sp, #48 |
| ; CHECK-NEXT: stp q0, q1, [sp] // 32-byte Folded Spill |
| ; CHECK-NEXT: mov v1.16b, v0.16b |
| ; CHECK-NEXT: str x30, [sp, #32] // 8-byte Spill |
| ; CHECK-NEXT: bl __unordtf2 |
| ; CHECK-NEXT: ldr q0, [sp, #16] // 16-byte Reload |
| ; CHECK-NEXT: cmp w0, #0 |
| ; CHECK-NEXT: b.eq .LBB16_2 |
| ; CHECK-NEXT: // %bb.1: |
| ; CHECK-NEXT: str q0, [sp] // 16-byte Spill |
| ; CHECK-NEXT: .LBB16_2: |
| ; CHECK-NEXT: mov v1.16b, v0.16b |
| ; CHECK-NEXT: bl __unordtf2 |
| ; CHECK-NEXT: ldp q0, q1, [sp] // 32-byte Folded Reload |
| ; CHECK-NEXT: cmp w0, #0 |
| ; CHECK-NEXT: b.eq .LBB16_4 |
| ; CHECK-NEXT: // %bb.3: |
| ; CHECK-NEXT: mov v1.16b, v0.16b |
| ; CHECK-NEXT: .LBB16_4: |
| ; CHECK-NEXT: ldr q0, [sp] // 16-byte Reload |
| ; CHECK-NEXT: str q1, [sp, #16] // 16-byte Spill |
| ; CHECK-NEXT: bl __gttf2 |
| ; CHECK-NEXT: ldr q0, [sp] // 16-byte Reload |
| ; CHECK-NEXT: cmp w0, #0 |
| ; CHECK-NEXT: b.le .LBB16_6 |
| ; CHECK-NEXT: // %bb.5: |
| ; CHECK-NEXT: str q0, [sp, #16] // 16-byte Spill |
| ; CHECK-NEXT: .LBB16_6: |
| ; CHECK-NEXT: str q0, [sp] // 16-byte Spill |
| ; CHECK-NEXT: bl __trunctfsf2 |
| ; CHECK-NEXT: fmov w8, s0 |
| ; CHECK-NEXT: ldr q0, [sp, #16] // 16-byte Reload |
| ; CHECK-NEXT: mov v1.16b, v0.16b |
| ; CHECK-NEXT: cmp w8, #0 |
| ; CHECK-NEXT: b.ne .LBB16_8 |
| ; CHECK-NEXT: // %bb.7: |
| ; CHECK-NEXT: ldr q1, [sp] // 16-byte Reload |
| ; CHECK-NEXT: .LBB16_8: |
| ; CHECK-NEXT: adrp x8, .LCPI16_0 |
| ; CHECK-NEXT: str q1, [sp] // 16-byte Spill |
| ; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI16_0] |
| ; CHECK-NEXT: bl __eqtf2 |
| ; CHECK-NEXT: ldr q0, [sp, #16] // 16-byte Reload |
| ; CHECK-NEXT: cmp w0, #0 |
| ; CHECK-NEXT: b.ne .LBB16_10 |
| ; CHECK-NEXT: // %bb.9: |
| ; CHECK-NEXT: ldr q0, [sp] // 16-byte Reload |
| ; CHECK-NEXT: .LBB16_10: |
| ; CHECK-NEXT: ldr x30, [sp, #32] // 8-byte Reload |
| ; CHECK-NEXT: add sp, sp, #48 |
| ; CHECK-NEXT: ret |
| %b = call fp128 @llvm.vector.reduce.fmaximumnum.v2f128(<2 x fp128> %a) |
| ret fp128 %b |
| } |
| |
| ; Needs widening rather than scalarizing. |
| ; The mvni constructs a NaN that is used as the identity element. |
| define float @test_v7f32(<7 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v7f32: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mvni v7.4s, #63, msl #16 |
| ; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0 |
| ; CHECK-NEXT: // kill: def $s4 killed $s4 def $q4 |
| ; CHECK-NEXT: // kill: def $s1 killed $s1 def $q1 |
| ; CHECK-NEXT: // kill: def $s5 killed $s5 def $q5 |
| ; CHECK-NEXT: // kill: def $s2 killed $s2 def $q2 |
| ; CHECK-NEXT: // kill: def $s6 killed $s6 def $q6 |
| ; CHECK-NEXT: // kill: def $s3 killed $s3 def $q3 |
| ; CHECK-NEXT: mov v0.s[1], v1.s[0] |
| ; CHECK-NEXT: mov v7.s[0], v4.s[0] |
| ; CHECK-NEXT: mov v0.s[2], v2.s[0] |
| ; CHECK-NEXT: mov v7.s[1], v5.s[0] |
| ; CHECK-NEXT: mov v0.s[3], v3.s[0] |
| ; CHECK-NEXT: mov v7.s[2], v6.s[0] |
| ; CHECK-NEXT: fminnm v0.4s, v0.4s, v0.4s |
| ; CHECK-NEXT: fminnm v1.4s, v7.4s, v7.4s |
| ; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v1.4s |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: mov s2, v0.s[2] |
| ; CHECK-NEXT: fmaxnm s1, s0, s1 |
| ; CHECK-NEXT: mov s0, v0.s[3] |
| ; CHECK-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call float @llvm.vector.reduce.fmaximumnum.v7f32(<7 x float> %a) |
| ret float %b |
| } |
| |
| ; The mvni constructs Inf that is used as the identity element. |
| ; That is valid because nnan means we don't need to consider NaN. |
| define float @test_v7f32_nnan(<7 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v7f32_nnan: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mvni v7.4s, #127, msl #16 |
| ; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0 |
| ; CHECK-NEXT: // kill: def $s4 killed $s4 def $q4 |
| ; CHECK-NEXT: // kill: def $s1 killed $s1 def $q1 |
| ; CHECK-NEXT: // kill: def $s5 killed $s5 def $q5 |
| ; CHECK-NEXT: // kill: def $s2 killed $s2 def $q2 |
| ; CHECK-NEXT: // kill: def $s6 killed $s6 def $q6 |
| ; CHECK-NEXT: // kill: def $s3 killed $s3 def $q3 |
| ; CHECK-NEXT: mov v0.s[1], v1.s[0] |
| ; CHECK-NEXT: mov v7.s[0], v4.s[0] |
| ; CHECK-NEXT: mov v0.s[2], v2.s[0] |
| ; CHECK-NEXT: mov v7.s[1], v5.s[0] |
| ; CHECK-NEXT: mov v0.s[3], v3.s[0] |
| ; CHECK-NEXT: mov v7.s[2], v6.s[0] |
| ; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v7.4s |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: mov s2, v0.s[2] |
| ; CHECK-NEXT: fmaxnm s1, s0, s1 |
| ; CHECK-NEXT: mov s0, v0.s[3] |
| ; CHECK-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call nnan float @llvm.vector.reduce.fmaximumnum.v7f32(<7 x float> %a) |
| ret float %b |
| } |
| |
| ; The mvni constructs -FLT_MAX that is used as the identity element. |
| ; That is valid because nnan ninf means we don't need to consider NaN or Inf. |
| define float @test_v7f32_nnan_ninf(<7 x float> %a) nounwind { |
| ; CHECK-LABEL: test_v7f32_nnan_ninf: |
| ; CHECK: // %bb.0: |
| ; CHECK-NEXT: mvni v7.4s, #128, lsl #16 |
| ; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0 |
| ; CHECK-NEXT: // kill: def $s4 killed $s4 def $q4 |
| ; CHECK-NEXT: // kill: def $s1 killed $s1 def $q1 |
| ; CHECK-NEXT: // kill: def $s5 killed $s5 def $q5 |
| ; CHECK-NEXT: // kill: def $s2 killed $s2 def $q2 |
| ; CHECK-NEXT: // kill: def $s6 killed $s6 def $q6 |
| ; CHECK-NEXT: // kill: def $s3 killed $s3 def $q3 |
| ; CHECK-NEXT: mov v0.s[1], v1.s[0] |
| ; CHECK-NEXT: mov v7.s[0], v4.s[0] |
| ; CHECK-NEXT: mov v0.s[2], v2.s[0] |
| ; CHECK-NEXT: mov v7.s[1], v5.s[0] |
| ; CHECK-NEXT: mov v0.s[3], v3.s[0] |
| ; CHECK-NEXT: mov v7.s[2], v6.s[0] |
| ; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v7.4s |
| ; CHECK-NEXT: mov s1, v0.s[1] |
| ; CHECK-NEXT: mov s2, v0.s[2] |
| ; CHECK-NEXT: fmaxnm s1, s0, s1 |
| ; CHECK-NEXT: mov s0, v0.s[3] |
| ; CHECK-NEXT: fmaxnm s1, s1, s2 |
| ; CHECK-NEXT: fmaxnm s0, s1, s0 |
| ; CHECK-NEXT: ret |
| %b = call nnan ninf float @llvm.vector.reduce.fmaximumnum.v7f32(<7 x float> %a) |
| ret float %b |
| } |
| ;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line: |
| ; CHECK-FP-GI: {{.*}} |
| ; CHECK-FP-SD: {{.*}} |
| ; CHECK-NOFP-GI: {{.*}} |
| ; CHECK-NOFP-SD: {{.*}} |
