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
120 lines
3.9 KiB
LLVM
120 lines
3.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+zfbfmin \
|
|
; RUN: -verify-machineinstrs -target-abi ilp32f | \
|
|
; RUN: FileCheck -check-prefixes=CHECK %s
|
|
; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+zfbfmin \
|
|
; RUN: -verify-machineinstrs -target-abi lp64f | \
|
|
; RUN: FileCheck -check-prefixes=CHECK %s
|
|
|
|
define bfloat @fminimum_bf16(bfloat %a, bfloat %b) nounwind {
|
|
; CHECK-LABEL: fminimum_bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
|
|
; CHECK-NEXT: feq.s a0, fa5, fa5
|
|
; CHECK-NEXT: fmv.s fa3, fa4
|
|
; CHECK-NEXT: bnez a0, .LBB0_2
|
|
; CHECK-NEXT: # %bb.1:
|
|
; CHECK-NEXT: fmv.s fa3, fa5
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: feq.s a0, fa4, fa4
|
|
; CHECK-NEXT: bnez a0, .LBB0_4
|
|
; CHECK-NEXT: # %bb.3:
|
|
; CHECK-NEXT: fmv.s fa5, fa4
|
|
; CHECK-NEXT: .LBB0_4:
|
|
; CHECK-NEXT: fmin.s fa5, fa5, fa3
|
|
; CHECK-NEXT: fcvt.bf16.s fa0, fa5
|
|
; CHECK-NEXT: ret
|
|
%1 = call bfloat @llvm.minimum.bf16(bfloat %a, bfloat %b)
|
|
ret bfloat %1
|
|
}
|
|
|
|
define bfloat @fmaximum_bf16(bfloat %a, bfloat %b) nounwind {
|
|
; CHECK-LABEL: fmaximum_bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
|
|
; CHECK-NEXT: feq.s a0, fa5, fa5
|
|
; CHECK-NEXT: fmv.s fa3, fa4
|
|
; CHECK-NEXT: bnez a0, .LBB1_2
|
|
; CHECK-NEXT: # %bb.1:
|
|
; CHECK-NEXT: fmv.s fa3, fa5
|
|
; CHECK-NEXT: .LBB1_2:
|
|
; CHECK-NEXT: feq.s a0, fa4, fa4
|
|
; CHECK-NEXT: bnez a0, .LBB1_4
|
|
; CHECK-NEXT: # %bb.3:
|
|
; CHECK-NEXT: fmv.s fa5, fa4
|
|
; CHECK-NEXT: .LBB1_4:
|
|
; CHECK-NEXT: fmax.s fa5, fa5, fa3
|
|
; CHECK-NEXT: fcvt.bf16.s fa0, fa5
|
|
; CHECK-NEXT: ret
|
|
%1 = call bfloat @llvm.maximum.bf16(bfloat %a, bfloat %b)
|
|
ret bfloat %1
|
|
}
|
|
|
|
define bfloat @fminimum_nnan_bf16(bfloat %a, bfloat %b) nounwind {
|
|
; CHECK-LABEL: fminimum_nnan_bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa0
|
|
; CHECK-NEXT: fmin.s fa5, fa4, fa5
|
|
; CHECK-NEXT: fcvt.bf16.s fa0, fa5
|
|
; CHECK-NEXT: ret
|
|
%1 = call nnan bfloat @llvm.minimum.bf16(bfloat %a, bfloat %b)
|
|
ret bfloat %1
|
|
}
|
|
|
|
define bfloat @fmaximum_nnan_bf16(bfloat %a, bfloat %b) nounwind {
|
|
; CHECK-LABEL: fmaximum_nnan_bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa0
|
|
; CHECK-NEXT: fmax.s fa5, fa4, fa5
|
|
; CHECK-NEXT: fcvt.bf16.s fa0, fa5
|
|
; CHECK-NEXT: ret
|
|
%1 = call nnan bfloat @llvm.maximum.bf16(bfloat %a, bfloat %b)
|
|
ret bfloat %1
|
|
}
|
|
|
|
define bfloat @fminimum_nnan_op_bf16(bfloat %a, bfloat %b) nounwind {
|
|
; CHECK-LABEL: fminimum_nnan_op_bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
|
|
; CHECK-NEXT: feq.s a0, fa5, fa5
|
|
; CHECK-NEXT: bnez a0, .LBB4_2
|
|
; CHECK-NEXT: # %bb.1:
|
|
; CHECK-NEXT: fmv.s fa4, fa5
|
|
; CHECK-NEXT: j .LBB4_3
|
|
; CHECK-NEXT: .LBB4_2:
|
|
; CHECK-NEXT: fadd.s fa4, fa5, fa5
|
|
; CHECK-NEXT: fcvt.bf16.s fa4, fa4
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa4
|
|
; CHECK-NEXT: .LBB4_3:
|
|
; CHECK-NEXT: fmin.s fa5, fa5, fa4
|
|
; CHECK-NEXT: fcvt.bf16.s fa0, fa5
|
|
; CHECK-NEXT: ret
|
|
%c = fadd nnan bfloat %a, %a
|
|
%1 = call bfloat @llvm.minimum.bf16(bfloat %a, bfloat %c)
|
|
ret bfloat %1
|
|
}
|
|
|
|
define bfloat @fmaximum_nnan_op_bf16(bfloat %a, bfloat %b) nounwind {
|
|
; CHECK-LABEL: fmaximum_nnan_op_bf16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa1
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa0
|
|
; CHECK-NEXT: fadd.s fa3, fa4, fa5
|
|
; CHECK-NEXT: fsub.s fa5, fa4, fa5
|
|
; CHECK-NEXT: fcvt.bf16.s fa4, fa3
|
|
; CHECK-NEXT: fcvt.bf16.s fa5, fa5
|
|
; CHECK-NEXT: fcvt.s.bf16 fa5, fa5
|
|
; CHECK-NEXT: fcvt.s.bf16 fa4, fa4
|
|
; CHECK-NEXT: fmax.s fa5, fa4, fa5
|
|
; CHECK-NEXT: fcvt.bf16.s fa0, fa5
|
|
; CHECK-NEXT: ret
|
|
%c = fadd nnan bfloat %a, %b
|
|
%d = fsub nnan bfloat %a, %b
|
|
%1 = call bfloat @llvm.maximum.bf16(bfloat %c, bfloat %d)
|
|
ret bfloat %1
|
|
}
|