Files
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

94 lines
4.8 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -stop-after=finalize-isel -o - %s | FileCheck %s
;; Test that reduction of:
;;
;; DST = shl i64 X, Y
;;
;; where Y is in the range [63-32] to:
;;
;; DST = [0, shl i32 X, (Y & 0x1F)]
;;
;; preserves flags
define i64 @shl_nsw(i64 %arg0, i64 %shift_amt) {
; CHECK-LABEL: name: shl_nsw
; CHECK: bb.0 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK-NEXT: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF1:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[DEF]]
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, killed [[COPY2]], %subreg.sub1
; CHECK-NEXT: [[DEF2:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF3:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[DEF2]]
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, killed [[COPY3]], %subreg.sub1
; CHECK-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE1]].sub0
; CHECK-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
; CHECK-NEXT: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = nsw V_LSHLREV_B32_e64 killed [[COPY4]], killed [[COPY5]], implicit $exec
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_MOV_B32_e32_]]
; CHECK-NEXT: $vgpr1 = COPY [[V_LSHLREV_B32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
%or = or i64 %shift_amt, 32
%shl = shl nsw i64 %arg0, %or
ret i64 %shl
}
define i64 @shl_nuw(i64 %arg0, i64 %shift_amt) {
; CHECK-LABEL: name: shl_nuw
; CHECK: bb.0 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK-NEXT: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF1:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[DEF]]
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, killed [[COPY2]], %subreg.sub1
; CHECK-NEXT: [[DEF2:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF3:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[DEF2]]
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, killed [[COPY3]], %subreg.sub1
; CHECK-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE1]].sub0
; CHECK-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
; CHECK-NEXT: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = nuw V_LSHLREV_B32_e64 killed [[COPY4]], killed [[COPY5]], implicit $exec
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_MOV_B32_e32_]]
; CHECK-NEXT: $vgpr1 = COPY [[V_LSHLREV_B32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
%or = or i64 %shift_amt, 32
%shl = shl nuw i64 %arg0, %or
ret i64 %shl
}
define i64 @shl_nsw_nuw(i64 %arg0, i64 %shift_amt) {
; CHECK-LABEL: name: shl_nsw_nuw
; CHECK: bb.0 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK-NEXT: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF1:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[DEF]]
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, killed [[COPY2]], %subreg.sub1
; CHECK-NEXT: [[DEF2:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[DEF3:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
; CHECK-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[DEF2]]
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, killed [[COPY3]], %subreg.sub1
; CHECK-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE1]].sub0
; CHECK-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
; CHECK-NEXT: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = nuw nsw V_LSHLREV_B32_e64 killed [[COPY4]], killed [[COPY5]], implicit $exec
; CHECK-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_MOV_B32_e32_]]
; CHECK-NEXT: $vgpr1 = COPY [[V_LSHLREV_B32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
%or = or i64 %shift_amt, 32
%shl = shl nsw nuw i64 %arg0, %or
ret i64 %shl
}