derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
250 lines
15 KiB
LLVM
250 lines
15 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc < %s -mtriple=arm -mattr=+vfp4d16sp,-fullfp16 -stop-after=finalize-isel | FileCheck %s --check-prefixes=CHECK-CVT
|
|
; RUN: llc < %s -mtriple=arm -mattr=+vfp4d16sp,+fullfp16 -stop-after=finalize-isel | FileCheck %s --check-prefixes=CHECK-FP16
|
|
|
|
; Check that the output instructions have the same fast math flags as the input
|
|
; fadd, even when f16 is legalized to f32.
|
|
; FIXME: We don't get fast math flags on VCVTBSH because the outermost node in
|
|
; the isel pattern is COPY_TO_REGCLASS and the fast math flags end up there.
|
|
|
|
define half @normal_fadd(half %x, half %y) {
|
|
; CHECK-CVT-LABEL: name: normal_fadd
|
|
; CHECK-CVT: bb.0.entry:
|
|
; CHECK-CVT-NEXT: liveins: $r0, $r1
|
|
; CHECK-CVT-NEXT: {{ $}}
|
|
; CHECK-CVT-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $r1
|
|
; CHECK-CVT-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $r0
|
|
; CHECK-CVT-NEXT: [[COPY2:%[0-9]+]]:spr = COPY [[COPY1]]
|
|
; CHECK-CVT-NEXT: [[COPY3:%[0-9]+]]:spr = COPY [[COPY]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS:%[0-9]+]]:spr = nofpexcept VCVTBHS killed [[COPY3]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VCVTBHS1:%[0-9]+]]:spr = nofpexcept VCVTBHS killed [[COPY2]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS:%[0-9]+]]:spr = nofpexcept VADDS killed [[VCVTBHS1]], killed [[VCVTBHS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF]], killed [[VADDS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY4:%[0-9]+]]:gpr = COPY killed [[VCVTBSH]]
|
|
; CHECK-CVT-NEXT: $r0 = COPY [[COPY4]]
|
|
; CHECK-CVT-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
;
|
|
; CHECK-FP16-LABEL: name: normal_fadd
|
|
; CHECK-FP16: bb.0.entry:
|
|
; CHECK-FP16-NEXT: liveins: $r0, $r1
|
|
; CHECK-FP16-NEXT: {{ $}}
|
|
; CHECK-FP16-NEXT: [[COPY:%[0-9]+]]:rgpr = COPY $r1
|
|
; CHECK-FP16-NEXT: [[COPY1:%[0-9]+]]:rgpr = COPY $r0
|
|
; CHECK-FP16-NEXT: [[VMOVHR:%[0-9]+]]:hpr = VMOVHR [[COPY]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VMOVHR1:%[0-9]+]]:hpr = VMOVHR [[COPY1]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH:%[0-9]+]]:hpr = nofpexcept VADDH killed [[VMOVHR1]], killed [[VMOVHR]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: $r0 = COPY [[VADDH]]
|
|
; CHECK-FP16-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
entry:
|
|
%add = fadd half %x, %y
|
|
ret half %add
|
|
}
|
|
|
|
define half @fast_fadd(half %x, half %y) {
|
|
; CHECK-CVT-LABEL: name: fast_fadd
|
|
; CHECK-CVT: bb.0.entry:
|
|
; CHECK-CVT-NEXT: liveins: $r0, $r1
|
|
; CHECK-CVT-NEXT: {{ $}}
|
|
; CHECK-CVT-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $r1
|
|
; CHECK-CVT-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $r0
|
|
; CHECK-CVT-NEXT: [[COPY2:%[0-9]+]]:spr = COPY [[COPY1]]
|
|
; CHECK-CVT-NEXT: [[COPY3:%[0-9]+]]:spr = COPY [[COPY]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc nofpexcept VCVTBHS killed [[COPY3]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VCVTBHS1:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc nofpexcept VCVTBHS killed [[COPY2]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc nofpexcept VADDS killed [[VCVTBHS1]], killed [[VCVTBHS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF]], killed [[VADDS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY4:%[0-9]+]]:gpr = COPY killed [[VCVTBSH]]
|
|
; CHECK-CVT-NEXT: $r0 = COPY [[COPY4]]
|
|
; CHECK-CVT-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
;
|
|
; CHECK-FP16-LABEL: name: fast_fadd
|
|
; CHECK-FP16: bb.0.entry:
|
|
; CHECK-FP16-NEXT: liveins: $r0, $r1
|
|
; CHECK-FP16-NEXT: {{ $}}
|
|
; CHECK-FP16-NEXT: [[COPY:%[0-9]+]]:rgpr = COPY $r1
|
|
; CHECK-FP16-NEXT: [[COPY1:%[0-9]+]]:rgpr = COPY $r0
|
|
; CHECK-FP16-NEXT: [[VMOVHR:%[0-9]+]]:hpr = VMOVHR [[COPY]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VMOVHR1:%[0-9]+]]:hpr = VMOVHR [[COPY1]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH:%[0-9]+]]:hpr = nnan ninf nsz arcp contract afn reassoc nofpexcept VADDH killed [[VMOVHR1]], killed [[VMOVHR]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: $r0 = COPY [[VADDH]]
|
|
; CHECK-FP16-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
entry:
|
|
%add = fadd fast half %x, %y
|
|
ret half %add
|
|
}
|
|
|
|
define half @ninf_fadd(half %x, half %y) {
|
|
; CHECK-CVT-LABEL: name: ninf_fadd
|
|
; CHECK-CVT: bb.0.entry:
|
|
; CHECK-CVT-NEXT: liveins: $r0, $r1
|
|
; CHECK-CVT-NEXT: {{ $}}
|
|
; CHECK-CVT-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $r1
|
|
; CHECK-CVT-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $r0
|
|
; CHECK-CVT-NEXT: [[COPY2:%[0-9]+]]:spr = COPY [[COPY1]]
|
|
; CHECK-CVT-NEXT: [[COPY3:%[0-9]+]]:spr = COPY [[COPY]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS:%[0-9]+]]:spr = ninf nofpexcept VCVTBHS killed [[COPY3]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VCVTBHS1:%[0-9]+]]:spr = ninf nofpexcept VCVTBHS killed [[COPY2]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS:%[0-9]+]]:spr = ninf nofpexcept VADDS killed [[VCVTBHS1]], killed [[VCVTBHS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF]], killed [[VADDS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY4:%[0-9]+]]:gpr = COPY killed [[VCVTBSH]]
|
|
; CHECK-CVT-NEXT: $r0 = COPY [[COPY4]]
|
|
; CHECK-CVT-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
;
|
|
; CHECK-FP16-LABEL: name: ninf_fadd
|
|
; CHECK-FP16: bb.0.entry:
|
|
; CHECK-FP16-NEXT: liveins: $r0, $r1
|
|
; CHECK-FP16-NEXT: {{ $}}
|
|
; CHECK-FP16-NEXT: [[COPY:%[0-9]+]]:rgpr = COPY $r1
|
|
; CHECK-FP16-NEXT: [[COPY1:%[0-9]+]]:rgpr = COPY $r0
|
|
; CHECK-FP16-NEXT: [[VMOVHR:%[0-9]+]]:hpr = VMOVHR [[COPY]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VMOVHR1:%[0-9]+]]:hpr = VMOVHR [[COPY1]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH:%[0-9]+]]:hpr = ninf nofpexcept VADDH killed [[VMOVHR1]], killed [[VMOVHR]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: $r0 = COPY [[VADDH]]
|
|
; CHECK-FP16-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
entry:
|
|
%add = fadd ninf half %x, %y
|
|
ret half %add
|
|
}
|
|
|
|
; Check that when we have the right fast math flags the converts in between the
|
|
; two fadds are removed.
|
|
|
|
define half @normal_fadd_sequence(half %x, half %y, half %z) {
|
|
; CHECK-CVT-LABEL: name: normal_fadd_sequence
|
|
; CHECK-CVT: bb.0.entry:
|
|
; CHECK-CVT-NEXT: liveins: $r0, $r1, $r2
|
|
; CHECK-CVT-NEXT: {{ $}}
|
|
; CHECK-CVT-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $r2
|
|
; CHECK-CVT-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $r1
|
|
; CHECK-CVT-NEXT: [[COPY2:%[0-9]+]]:gpr = COPY $r0
|
|
; CHECK-CVT-NEXT: [[COPY3:%[0-9]+]]:spr = COPY [[COPY2]]
|
|
; CHECK-CVT-NEXT: [[COPY4:%[0-9]+]]:spr = COPY [[COPY1]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS:%[0-9]+]]:spr = nofpexcept VCVTBHS killed [[COPY4]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VCVTBHS1:%[0-9]+]]:spr = nofpexcept VCVTBHS killed [[COPY3]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS:%[0-9]+]]:spr = nofpexcept VADDS killed [[VCVTBHS1]], killed [[VCVTBHS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY5:%[0-9]+]]:spr = COPY [[COPY]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS2:%[0-9]+]]:spr = nofpexcept VCVTBHS killed [[COPY5]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF]], killed [[VADDS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY6:%[0-9]+]]:gpr = COPY killed [[VCVTBSH]]
|
|
; CHECK-CVT-NEXT: [[COPY7:%[0-9]+]]:spr = COPY killed [[COPY6]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS3:%[0-9]+]]:spr = nofpexcept VCVTBHS killed [[COPY7]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS1:%[0-9]+]]:spr = nofpexcept VADDS killed [[VCVTBHS3]], killed [[VCVTBHS2]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF1:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH1:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF1]], killed [[VADDS1]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY8:%[0-9]+]]:gpr = COPY killed [[VCVTBSH1]]
|
|
; CHECK-CVT-NEXT: $r0 = COPY [[COPY8]]
|
|
; CHECK-CVT-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
;
|
|
; CHECK-FP16-LABEL: name: normal_fadd_sequence
|
|
; CHECK-FP16: bb.0.entry:
|
|
; CHECK-FP16-NEXT: liveins: $r0, $r1, $r2
|
|
; CHECK-FP16-NEXT: {{ $}}
|
|
; CHECK-FP16-NEXT: [[COPY:%[0-9]+]]:rgpr = COPY $r2
|
|
; CHECK-FP16-NEXT: [[COPY1:%[0-9]+]]:rgpr = COPY $r1
|
|
; CHECK-FP16-NEXT: [[COPY2:%[0-9]+]]:rgpr = COPY $r0
|
|
; CHECK-FP16-NEXT: [[VMOVHR:%[0-9]+]]:hpr = VMOVHR [[COPY1]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VMOVHR1:%[0-9]+]]:hpr = VMOVHR [[COPY2]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH:%[0-9]+]]:hpr = nofpexcept VADDH killed [[VMOVHR1]], killed [[VMOVHR]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: [[VMOVHR2:%[0-9]+]]:hpr = VMOVHR [[COPY]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH1:%[0-9]+]]:hpr = nofpexcept VADDH killed [[VADDH]], killed [[VMOVHR2]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: $r0 = COPY [[VADDH1]]
|
|
; CHECK-FP16-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
entry:
|
|
%add1 = fadd half %x, %y
|
|
%add2 = fadd half %add1, %z
|
|
ret half %add2
|
|
}
|
|
|
|
define half @nnan_ninf_contract_fadd_sequence(half %x, half %y, half %z) {
|
|
; CHECK-CVT-LABEL: name: nnan_ninf_contract_fadd_sequence
|
|
; CHECK-CVT: bb.0.entry:
|
|
; CHECK-CVT-NEXT: liveins: $r0, $r1, $r2
|
|
; CHECK-CVT-NEXT: {{ $}}
|
|
; CHECK-CVT-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $r2
|
|
; CHECK-CVT-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $r1
|
|
; CHECK-CVT-NEXT: [[COPY2:%[0-9]+]]:gpr = COPY $r0
|
|
; CHECK-CVT-NEXT: [[COPY3:%[0-9]+]]:spr = COPY [[COPY2]]
|
|
; CHECK-CVT-NEXT: [[COPY4:%[0-9]+]]:spr = COPY [[COPY1]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS:%[0-9]+]]:spr = nnan ninf contract nofpexcept VCVTBHS killed [[COPY4]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VCVTBHS1:%[0-9]+]]:spr = nnan ninf contract nofpexcept VCVTBHS killed [[COPY3]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS:%[0-9]+]]:spr = nnan ninf contract nofpexcept VADDS killed [[VCVTBHS1]], killed [[VCVTBHS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY5:%[0-9]+]]:spr = COPY [[COPY]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS2:%[0-9]+]]:spr = nnan ninf contract nofpexcept VCVTBHS killed [[COPY5]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS1:%[0-9]+]]:spr = nnan ninf contract nofpexcept VADDS killed [[VADDS]], killed [[VCVTBHS2]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF]], killed [[VADDS1]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY6:%[0-9]+]]:gpr = COPY killed [[VCVTBSH]]
|
|
; CHECK-CVT-NEXT: $r0 = COPY [[COPY6]]
|
|
; CHECK-CVT-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
;
|
|
; CHECK-FP16-LABEL: name: nnan_ninf_contract_fadd_sequence
|
|
; CHECK-FP16: bb.0.entry:
|
|
; CHECK-FP16-NEXT: liveins: $r0, $r1, $r2
|
|
; CHECK-FP16-NEXT: {{ $}}
|
|
; CHECK-FP16-NEXT: [[COPY:%[0-9]+]]:rgpr = COPY $r2
|
|
; CHECK-FP16-NEXT: [[COPY1:%[0-9]+]]:rgpr = COPY $r1
|
|
; CHECK-FP16-NEXT: [[COPY2:%[0-9]+]]:rgpr = COPY $r0
|
|
; CHECK-FP16-NEXT: [[VMOVHR:%[0-9]+]]:hpr = VMOVHR [[COPY1]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VMOVHR1:%[0-9]+]]:hpr = VMOVHR [[COPY2]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH:%[0-9]+]]:hpr = nnan ninf contract nofpexcept VADDH killed [[VMOVHR1]], killed [[VMOVHR]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: [[VMOVHR2:%[0-9]+]]:hpr = VMOVHR [[COPY]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH1:%[0-9]+]]:hpr = nnan ninf contract nofpexcept VADDH killed [[VADDH]], killed [[VMOVHR2]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: $r0 = COPY [[VADDH1]]
|
|
; CHECK-FP16-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
entry:
|
|
%add1 = fadd nnan ninf contract half %x, %y
|
|
%add2 = fadd nnan ninf contract half %add1, %z
|
|
ret half %add2
|
|
}
|
|
|
|
define half @ninf_fadd_sequence(half %x, half %y, half %z) {
|
|
; CHECK-CVT-LABEL: name: ninf_fadd_sequence
|
|
; CHECK-CVT: bb.0.entry:
|
|
; CHECK-CVT-NEXT: liveins: $r0, $r1, $r2
|
|
; CHECK-CVT-NEXT: {{ $}}
|
|
; CHECK-CVT-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $r2
|
|
; CHECK-CVT-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $r1
|
|
; CHECK-CVT-NEXT: [[COPY2:%[0-9]+]]:gpr = COPY $r0
|
|
; CHECK-CVT-NEXT: [[COPY3:%[0-9]+]]:spr = COPY [[COPY2]]
|
|
; CHECK-CVT-NEXT: [[COPY4:%[0-9]+]]:spr = COPY [[COPY1]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS:%[0-9]+]]:spr = ninf nofpexcept VCVTBHS killed [[COPY4]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VCVTBHS1:%[0-9]+]]:spr = ninf nofpexcept VCVTBHS killed [[COPY3]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS:%[0-9]+]]:spr = ninf nofpexcept VADDS killed [[VCVTBHS1]], killed [[VCVTBHS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY5:%[0-9]+]]:spr = COPY [[COPY]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS2:%[0-9]+]]:spr = ninf nofpexcept VCVTBHS killed [[COPY5]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF]], killed [[VADDS]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY6:%[0-9]+]]:gpr = COPY killed [[VCVTBSH]]
|
|
; CHECK-CVT-NEXT: [[COPY7:%[0-9]+]]:spr = COPY killed [[COPY6]]
|
|
; CHECK-CVT-NEXT: [[VCVTBHS3:%[0-9]+]]:spr = ninf nofpexcept VCVTBHS killed [[COPY7]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[VADDS1:%[0-9]+]]:spr = ninf nofpexcept VADDS killed [[VCVTBHS3]], killed [[VCVTBHS2]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[DEF1:%[0-9]+]]:spr = IMPLICIT_DEF
|
|
; CHECK-CVT-NEXT: [[VCVTBSH1:%[0-9]+]]:spr = nofpexcept VCVTBSH [[DEF1]], killed [[VADDS1]], 14 /* CC::al */, $noreg, implicit $fpscr
|
|
; CHECK-CVT-NEXT: [[COPY8:%[0-9]+]]:gpr = COPY killed [[VCVTBSH1]]
|
|
; CHECK-CVT-NEXT: $r0 = COPY [[COPY8]]
|
|
; CHECK-CVT-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
;
|
|
; CHECK-FP16-LABEL: name: ninf_fadd_sequence
|
|
; CHECK-FP16: bb.0.entry:
|
|
; CHECK-FP16-NEXT: liveins: $r0, $r1, $r2
|
|
; CHECK-FP16-NEXT: {{ $}}
|
|
; CHECK-FP16-NEXT: [[COPY:%[0-9]+]]:rgpr = COPY $r2
|
|
; CHECK-FP16-NEXT: [[COPY1:%[0-9]+]]:rgpr = COPY $r1
|
|
; CHECK-FP16-NEXT: [[COPY2:%[0-9]+]]:rgpr = COPY $r0
|
|
; CHECK-FP16-NEXT: [[VMOVHR:%[0-9]+]]:hpr = VMOVHR [[COPY1]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VMOVHR1:%[0-9]+]]:hpr = VMOVHR [[COPY2]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH:%[0-9]+]]:hpr = ninf nofpexcept VADDH killed [[VMOVHR1]], killed [[VMOVHR]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: [[VMOVHR2:%[0-9]+]]:hpr = VMOVHR [[COPY]], 14, $noreg
|
|
; CHECK-FP16-NEXT: [[VADDH1:%[0-9]+]]:hpr = ninf nofpexcept VADDH killed [[VADDH]], killed [[VMOVHR2]], 14, $noreg, implicit $fpscr
|
|
; CHECK-FP16-NEXT: $r0 = COPY [[VADDH1]]
|
|
; CHECK-FP16-NEXT: MOVPCLR 14 /* CC::al */, $noreg, implicit $r0
|
|
entry:
|
|
%add1 = fadd ninf half %x, %y
|
|
%add2 = fadd ninf half %add1, %z
|
|
ret half %add2
|
|
}
|