150 lines
4.9 KiB
LLVM
150 lines
4.9 KiB
LLVM
; 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
|
|
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon,+fullfp16 | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP
|
|
|
|
declare half @llvm.vector.reduce.fmax.v1f16(<1 x half> %a)
|
|
declare float @llvm.vector.reduce.fmax.v1f32(<1 x float> %a)
|
|
declare double @llvm.vector.reduce.fmax.v1f64(<1 x double> %a)
|
|
declare fp128 @llvm.vector.reduce.fmax.v1f128(<1 x fp128> %a)
|
|
|
|
declare half @llvm.vector.reduce.fmax.v4f16(<4 x half> %a)
|
|
declare float @llvm.vector.reduce.fmax.v3f32(<3 x float> %a)
|
|
declare fp128 @llvm.vector.reduce.fmax.v2f128(<2 x fp128> %a)
|
|
declare float @llvm.vector.reduce.fmax.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.vector.reduce.fmax.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.vector.reduce.fmax.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.vector.reduce.fmax.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.vector.reduce.fmax.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 h3, v0.h[1]
|
|
; CHECK-NOFP-NEXT: mov h1, v0.h[3]
|
|
; CHECK-NOFP-NEXT: mov h2, v0.h[2]
|
|
; CHECK-NOFP-NEXT: fcvt s0, h0
|
|
; CHECK-NOFP-NEXT: fcvt s3, h3
|
|
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s3
|
|
; CHECK-NOFP-NEXT: fcvt h0, s0
|
|
; CHECK-NOFP-NEXT: fcvt s2, h2
|
|
; CHECK-NOFP-NEXT: fcvt s0, h0
|
|
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s2
|
|
; CHECK-NOFP-NEXT: fcvt h0, s0
|
|
; CHECK-NOFP-NEXT: fcvt s0, h0
|
|
; CHECK-NOFP-NEXT: fcvt s1, h1
|
|
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
|
|
; CHECK-NOFP-NEXT: fcvt h0, s0
|
|
; CHECK-NOFP-NEXT: ret
|
|
;
|
|
; CHECK-FP-LABEL: test_v4f16:
|
|
; CHECK-FP: // %bb.0:
|
|
; CHECK-FP-NEXT: fmaxnmv h0, v0.4h
|
|
; CHECK-FP-NEXT: ret
|
|
%b = call nnan half @llvm.vector.reduce.fmax.v4f16(<4 x half> %a)
|
|
ret half %b
|
|
}
|
|
|
|
define half @test_v4f16_ninf(<4 x half> %a) nounwind {
|
|
; CHECK-NOFP-LABEL: test_v4f16_ninf:
|
|
; CHECK-NOFP: // %bb.0:
|
|
; CHECK-NOFP-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NOFP-NEXT: mov h3, v0.h[1]
|
|
; CHECK-NOFP-NEXT: mov h1, v0.h[3]
|
|
; CHECK-NOFP-NEXT: mov h2, v0.h[2]
|
|
; CHECK-NOFP-NEXT: fcvt s0, h0
|
|
; CHECK-NOFP-NEXT: fcvt s3, h3
|
|
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s3
|
|
; CHECK-NOFP-NEXT: fcvt h0, s0
|
|
; CHECK-NOFP-NEXT: fcvt s2, h2
|
|
; CHECK-NOFP-NEXT: fcvt s0, h0
|
|
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s2
|
|
; CHECK-NOFP-NEXT: fcvt h0, s0
|
|
; CHECK-NOFP-NEXT: fcvt s0, h0
|
|
; CHECK-NOFP-NEXT: fcvt s1, h1
|
|
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
|
|
; CHECK-NOFP-NEXT: fcvt h0, s0
|
|
; CHECK-NOFP-NEXT: ret
|
|
;
|
|
; CHECK-FP-LABEL: test_v4f16_ninf:
|
|
; CHECK-FP: // %bb.0:
|
|
; CHECK-FP-NEXT: fmaxnmv h0, v0.4h
|
|
; CHECK-FP-NEXT: ret
|
|
%b = call nnan ninf half @llvm.vector.reduce.fmax.v4f16(<4 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 w8, #-8388608
|
|
; 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.vector.reduce.fmax.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 w8, #-8388609
|
|
; 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 ninf float @llvm.vector.reduce.fmax.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.vector.reduce.fmax.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.vector.reduce.fmax.v16f32(<16 x float> %a)
|
|
ret float %b
|
|
}
|