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

233 lines
9.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -mtriple=x86_64-linux -codegenprepare -S | FileCheck %s
; No overflow flags, same type width.
define i32 @test_01(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: @test_01(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[COND_1:%.*]] = icmp eq i64 [[IV]], [[LEN:%.*]]
; CHECK-NEXT: br i1 [[COND_1]], label [[EXIT:%.*]], label [[BACKEDGE]]
; CHECK: backedge:
; CHECK-NEXT: [[SUNKADDR:%.*]] = mul i64 [[IV_NEXT]], 4
; CHECK-NEXT: [[SUNKADDR1:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[SUNKADDR]]
; CHECK-NEXT: [[SUNKADDR2:%.*]] = getelementptr i8, ptr [[SUNKADDR1]], i64 -8
; CHECK-NEXT: [[LOADED:%.*]] = load atomic i32, ptr [[SUNKADDR2]] unordered, align 4
; CHECK-NEXT: [[COND_2:%.*]] = icmp eq i32 [[LOADED]], [[X:%.*]]
; CHECK-NEXT: br i1 [[COND_2]], label [[FAILURE:%.*]], label [[LOOP]]
; CHECK: exit:
; CHECK-NEXT: ret i32 -1
; CHECK: failure:
; CHECK-NEXT: unreachable
;
entry:
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add i64 %iv, 1
%cond_1 = icmp eq i64 %iv, %len
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nsw flag, same type width.
define i32 @test_02(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: @test_02(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[IV_NEXT]] = add nsw i64 [[IV]], 1
; CHECK-NEXT: [[COND_1:%.*]] = icmp eq i64 [[IV]], [[LEN:%.*]]
; CHECK-NEXT: br i1 [[COND_1]], label [[EXIT:%.*]], label [[BACKEDGE]]
; CHECK: backedge:
; CHECK-NEXT: [[SUNKADDR:%.*]] = mul i64 [[IV]], 4
; CHECK-NEXT: [[SUNKADDR1:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[SUNKADDR]]
; CHECK-NEXT: [[SUNKADDR2:%.*]] = getelementptr i8, ptr [[SUNKADDR1]], i64 -4
; CHECK-NEXT: [[LOADED:%.*]] = load atomic i32, ptr [[SUNKADDR2]] unordered, align 4
; CHECK-NEXT: [[COND_2:%.*]] = icmp eq i32 [[LOADED]], [[X:%.*]]
; CHECK-NEXT: br i1 [[COND_2]], label [[FAILURE:%.*]], label [[LOOP]]
; CHECK: exit:
; CHECK-NEXT: ret i32 -1
; CHECK: failure:
; CHECK-NEXT: unreachable
;
entry:
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nsw i64 %iv, 1
%cond_1 = icmp eq i64 %iv, %len
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nsw flag, optimization is possible because memory instruction is dominated by loop-exiting check against iv.next.
define i32 @test_02_nopoison(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: @test_02_nopoison(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[LEN_PLUS_1:%.*]] = add i64 [[LEN:%.*]], 1
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[IV_NEXT]] = add nsw i64 [[IV]], 1
; CHECK-NEXT: [[COND_1:%.*]] = icmp eq i64 [[IV_NEXT]], [[LEN_PLUS_1]]
; CHECK-NEXT: br i1 [[COND_1]], label [[EXIT:%.*]], label [[BACKEDGE]]
; CHECK: backedge:
; CHECK-NEXT: [[SUNKADDR:%.*]] = mul i64 [[IV]], 4
; CHECK-NEXT: [[SUNKADDR1:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[SUNKADDR]]
; CHECK-NEXT: [[SUNKADDR2:%.*]] = getelementptr i8, ptr [[SUNKADDR1]], i64 -4
; CHECK-NEXT: [[LOADED:%.*]] = load atomic i32, ptr [[SUNKADDR2]] unordered, align 4
; CHECK-NEXT: [[COND_2:%.*]] = icmp eq i32 [[LOADED]], [[X:%.*]]
; CHECK-NEXT: br i1 [[COND_2]], label [[FAILURE:%.*]], label [[LOOP]]
; CHECK: exit:
; CHECK-NEXT: ret i32 -1
; CHECK: failure:
; CHECK-NEXT: unreachable
;
entry:
%len.plus.1 = add i64 %len, 1
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nsw i64 %iv, 1
%cond_1 = icmp eq i64 %iv.next, %len.plus.1
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nuw flag, same type width.
define i32 @test_03(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: @test_03(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[IV_NEXT]] = add nuw i64 [[IV]], 1
; CHECK-NEXT: [[COND_1:%.*]] = icmp eq i64 [[IV]], [[LEN:%.*]]
; CHECK-NEXT: br i1 [[COND_1]], label [[EXIT:%.*]], label [[BACKEDGE]]
; CHECK: backedge:
; CHECK-NEXT: [[SUNKADDR:%.*]] = mul i64 [[IV]], 4
; CHECK-NEXT: [[SUNKADDR1:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[SUNKADDR]]
; CHECK-NEXT: [[SUNKADDR2:%.*]] = getelementptr i8, ptr [[SUNKADDR1]], i64 -4
; CHECK-NEXT: [[LOADED:%.*]] = load atomic i32, ptr [[SUNKADDR2]] unordered, align 4
; CHECK-NEXT: [[COND_2:%.*]] = icmp eq i32 [[LOADED]], [[X:%.*]]
; CHECK-NEXT: br i1 [[COND_2]], label [[FAILURE:%.*]], label [[LOOP]]
; CHECK: exit:
; CHECK-NEXT: ret i32 -1
; CHECK: failure:
; CHECK-NEXT: unreachable
;
entry:
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nuw i64 %iv, 1
%cond_1 = icmp eq i64 %iv, %len
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nuw flag, optimization is possible because memory instruction is dominated by loop-exiting check against iv.next.
define i32 @test_03_nopoison(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: @test_03_nopoison(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[LEN_PLUS_1:%.*]] = add i64 [[LEN:%.*]], 1
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[IV_NEXT]] = add nuw i64 [[IV]], 1
; CHECK-NEXT: [[COND_1:%.*]] = icmp eq i64 [[IV_NEXT]], [[LEN_PLUS_1]]
; CHECK-NEXT: br i1 [[COND_1]], label [[EXIT:%.*]], label [[BACKEDGE]]
; CHECK: backedge:
; CHECK-NEXT: [[SUNKADDR:%.*]] = mul i64 [[IV]], 4
; CHECK-NEXT: [[SUNKADDR1:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[SUNKADDR]]
; CHECK-NEXT: [[SUNKADDR2:%.*]] = getelementptr i8, ptr [[SUNKADDR1]], i64 -4
; CHECK-NEXT: [[LOADED:%.*]] = load atomic i32, ptr [[SUNKADDR2]] unordered, align 4
; CHECK-NEXT: [[COND_2:%.*]] = icmp eq i32 [[LOADED]], [[X:%.*]]
; CHECK-NEXT: br i1 [[COND_2]], label [[FAILURE:%.*]], label [[LOOP]]
; CHECK: exit:
; CHECK-NEXT: ret i32 -1
; CHECK: failure:
; CHECK-NEXT: unreachable
;
entry:
%len.plus.1 = add i64 %len, 1
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nuw i64 %iv, 1
%cond_1 = icmp eq i64 %iv.next, %len.plus.1
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}