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
74 lines
2.9 KiB
LLVM
74 lines
2.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: opt -S -passes=licm < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
define i64 @sve_uaddv(<vscale x 4 x i32> %inv, i1 %c) {
|
|
; CHECK-LABEL: define i64 @sve_uaddv(
|
|
; CHECK-SAME: <vscale x 4 x i32> [[INV:%.*]], i1 [[C:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[UADDV:%.*]] = call i64 @llvm.aarch64.sve.uaddv.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[INV]])
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
|
|
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
|
|
; CHECK-NEXT: [[BACKEDGE_COND:%.*]] = icmp ult i64 [[IV]], [[UADDV]]
|
|
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[C]], i1 [[BACKEDGE_COND]], i1 false
|
|
; CHECK-NEXT: br i1 [[OR_COND]], label %[[LOOP]], label %[[EXIT:.*]]
|
|
; CHECK: [[EXIT]]:
|
|
; CHECK-NEXT: [[IV_LCSSA:%.*]] = phi i64 [ [[IV]], %[[LOOP]] ]
|
|
; CHECK-NEXT: ret i64 [[IV_LCSSA]]
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %cond.true ]
|
|
%iv.next = add i64 %iv, 1
|
|
br i1 %c, label %cond.true, label %exit
|
|
|
|
cond.true:
|
|
%uaddv = call i64 @llvm.aarch64.sve.uaddv.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> %inv)
|
|
%backedge.cond = icmp ult i64 %iv, %uaddv
|
|
br i1 %backedge.cond, label %loop, label %exit
|
|
|
|
exit:
|
|
ret i64 %iv
|
|
}
|
|
|
|
define i64 @sve_faddv(<vscale x 4 x float> %inv, i1 %c) {
|
|
; CHECK-LABEL: define i64 @sve_faddv(
|
|
; CHECK-SAME: <vscale x 4 x float> [[INV:%.*]], i1 [[C:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[COND_TRUE:.*]] ]
|
|
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
|
|
; CHECK-NEXT: br i1 [[C]], label %[[COND_TRUE]], label %[[EXIT:.*]]
|
|
; CHECK: [[COND_TRUE]]:
|
|
; CHECK-NEXT: [[FADDV:%.*]] = call float @llvm.aarch64.sve.faddv.nxv4f32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> [[INV]])
|
|
; CHECK-NEXT: [[IV_AS_FLOAT:%.*]] = sitofp i64 [[IV]] to float
|
|
; CHECK-NEXT: [[BACKEDGE_COND:%.*]] = fcmp olt float [[IV_AS_FLOAT]], [[FADDV]]
|
|
; CHECK-NEXT: br i1 [[BACKEDGE_COND]], label %[[LOOP]], label %[[EXIT]]
|
|
; CHECK: [[EXIT]]:
|
|
; CHECK-NEXT: [[IV_LCSSA:%.*]] = phi i64 [ [[IV]], %[[COND_TRUE]] ], [ [[IV]], %[[LOOP]] ]
|
|
; CHECK-NEXT: ret i64 [[IV_LCSSA]]
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %cond.true ]
|
|
%iv.next = add i64 %iv, 1
|
|
br i1 %c, label %cond.true, label %exit
|
|
|
|
cond.true:
|
|
%faddv = call float @llvm.aarch64.sve.faddv.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x float> %inv)
|
|
%iv.as.float = sitofp i64 %iv to float
|
|
%backedge.cond = fcmp olt float %iv.as.float, %faddv
|
|
br i1 %backedge.cond, label %loop, label %exit
|
|
|
|
exit:
|
|
ret i64 %iv
|
|
}
|