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
249 lines
10 KiB
LLVM
249 lines
10 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -passes='print<access-info><allow-partial>' -disable-output %s 2>&1 | FileCheck %s
|
|
|
|
|
|
define void @dependency_check_and_runtime_checks_needed_select_of_invariant_ptrs(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
|
|
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_invariant_ptrs'
|
|
; CHECK-NEXT: loop:
|
|
; CHECK-NEXT: Memory dependences are safe with run-time checks
|
|
; CHECK-NEXT: Dependences:
|
|
; CHECK-NEXT: Run-time memory checks:
|
|
; CHECK-NEXT: Check 0:
|
|
; CHECK-NEXT: Comparing group GRP0:
|
|
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
; CHECK-NEXT: Against group GRP1:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
|
|
; CHECK-NEXT: Check 1:
|
|
; CHECK-NEXT: Comparing group GRP0:
|
|
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
; CHECK-NEXT: Against group GRP2:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
|
|
; CHECK-NEXT: Check 2:
|
|
; CHECK-NEXT: Comparing group GRP0:
|
|
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
; CHECK-NEXT: Against group GRP3:
|
|
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
; CHECK-NEXT: Check 3:
|
|
; CHECK-NEXT: Comparing group GRP1:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
|
|
; CHECK-NEXT: Against group GRP3:
|
|
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
; CHECK-NEXT: Check 4:
|
|
; CHECK-NEXT: Comparing group GRP2:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
|
|
; CHECK-NEXT: Against group GRP3:
|
|
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
; CHECK-NEXT: Grouped accesses:
|
|
; CHECK-NEXT: Group GRP0:
|
|
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
|
|
; CHECK-NEXT: Group GRP1:
|
|
; CHECK-NEXT: (Low: %b High: (4 + %b))
|
|
; CHECK-NEXT: Member: %b
|
|
; CHECK-NEXT: Group GRP2:
|
|
; CHECK-NEXT: (Low: %c High: (4 + %c))
|
|
; CHECK-NEXT: Member: %c
|
|
; CHECK-NEXT: Group GRP3:
|
|
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
|
|
; CHECK-NEXT: SCEV assumptions:
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Expressions re-written:
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
%l1 = load float, ptr %gep.a.iv, align 4
|
|
%iv.offset = add i64 %iv, %offset
|
|
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
%l2 = load float, ptr %gep.a.iv.off, align 4
|
|
%ad = fadd fast float %l1, %l2
|
|
store float %ad, ptr %gep.a.iv, align 4
|
|
%cmp = fcmp ult float %l1, 10.0
|
|
%select = select i1 %cmp, ptr %b, ptr %c
|
|
store float 0.0, ptr %select
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond = icmp eq i64 %iv.next, %n
|
|
br i1 %exitcond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
|
|
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs'
|
|
; CHECK-NEXT: loop:
|
|
; CHECK-NEXT: Memory dependences are safe with run-time checks
|
|
; CHECK-NEXT: Dependences:
|
|
; CHECK-NEXT: Run-time memory checks:
|
|
; CHECK-NEXT: Check 0:
|
|
; CHECK-NEXT: Comparing group GRP0:
|
|
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
; CHECK-NEXT: Against group GRP1:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
|
|
; CHECK-NEXT: Check 1:
|
|
; CHECK-NEXT: Comparing group GRP0:
|
|
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
; CHECK-NEXT: Against group GRP2:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
|
|
; CHECK-NEXT: Check 2:
|
|
; CHECK-NEXT: Comparing group GRP0:
|
|
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
; CHECK-NEXT: Against group GRP3:
|
|
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
; CHECK-NEXT: Check 3:
|
|
; CHECK-NEXT: Comparing group GRP1:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
|
|
; CHECK-NEXT: Against group GRP3:
|
|
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
; CHECK-NEXT: Check 4:
|
|
; CHECK-NEXT: Comparing group GRP2:
|
|
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
|
|
; CHECK-NEXT: Against group GRP3:
|
|
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
; CHECK-NEXT: Grouped accesses:
|
|
; CHECK-NEXT: Group GRP0:
|
|
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
|
|
; CHECK-NEXT: Group GRP1:
|
|
; CHECK-NEXT: (Low: %b High: ((4 * %n) + %b))
|
|
; CHECK-NEXT: Member: {%b,+,4}<%loop>
|
|
; CHECK-NEXT: Group GRP2:
|
|
; CHECK-NEXT: (Low: %c High: ((4 * %n) + %c))
|
|
; CHECK-NEXT: Member: {%c,+,4}<%loop>
|
|
; CHECK-NEXT: Group GRP3:
|
|
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
|
|
; CHECK-NEXT: SCEV assumptions:
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Expressions re-written:
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
%l1 = load float, ptr %gep.a.iv, align 4
|
|
%iv.offset = add i64 %iv, %offset
|
|
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
%l2 = load float, ptr %gep.a.iv.off, align 4
|
|
%ad = fadd fast float %l1, %l2
|
|
store float %ad, ptr %gep.a.iv, align 4
|
|
%gep.b = getelementptr inbounds float, ptr %b, i64 %iv
|
|
%gep.c = getelementptr inbounds float, ptr %c, i64 %iv
|
|
%cmp = fcmp ult float %l1, 10.0
|
|
%select = select i1 %cmp, ptr %gep.b, ptr %gep.c
|
|
store float 0.0, ptr %select
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond = icmp eq i64 %iv.next, %n
|
|
br i1 %exitcond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_1(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
|
|
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_1'
|
|
; CHECK-NEXT: loop:
|
|
; CHECK-NEXT: Report: cannot identify array bounds
|
|
; CHECK-NEXT: Dependences:
|
|
; CHECK-NEXT: Run-time memory checks:
|
|
; CHECK-NEXT: Grouped accesses:
|
|
; CHECK-NEXT: Group GRP0:
|
|
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
|
|
; CHECK-NEXT: Group GRP1:
|
|
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
|
|
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
|
|
; CHECK-NEXT: Generated run-time checks are incomplete
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
|
|
; CHECK-NEXT: SCEV assumptions:
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Expressions re-written:
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%iv2 = phi i64 [ 0, %entry ], [ %iv2.next, %loop ]
|
|
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
%l1 = load float, ptr %gep.a.iv, align 4
|
|
%iv.offset = add i64 %iv, %offset
|
|
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
%l2 = load float, ptr %gep.a.iv.off, align 4
|
|
%ad = fadd fast float %l1, %l2
|
|
store float %ad, ptr %gep.a.iv, align 4
|
|
%gep.b = getelementptr float, ptr %b, i64 %iv2
|
|
%gep.c = getelementptr inbounds float, ptr %c, i64 %iv
|
|
%cmp = fcmp ult float %l1, 10.0
|
|
%select = select i1 %cmp, ptr %gep.b, ptr %gep.c
|
|
store float 0.0, ptr %select
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%iv2.next = add i64 %iv2, 2
|
|
%exitcond = icmp eq i64 %iv.next, %n
|
|
br i1 %exitcond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
|
|
define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_2(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
|
|
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_2'
|
|
; CHECK-NEXT: loop:
|
|
; CHECK-NEXT: Report: cannot identify array bounds
|
|
; CHECK-NEXT: Dependences:
|
|
; CHECK-NEXT: Run-time memory checks:
|
|
; CHECK-NEXT: Grouped accesses:
|
|
; CHECK-NEXT: Group GRP0:
|
|
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
|
|
; CHECK-NEXT: Group GRP1:
|
|
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
|
|
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
|
|
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
|
|
; CHECK-NEXT: Generated run-time checks are incomplete
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
|
|
; CHECK-NEXT: SCEV assumptions:
|
|
; CHECK-EMPTY:
|
|
; CHECK-NEXT: Expressions re-written:
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%iv2 = phi i64 [ 0, %entry ], [ %iv2.next, %loop ]
|
|
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
|
|
%l1 = load float, ptr %gep.a.iv, align 4
|
|
%iv.offset = add i64 %iv, %offset
|
|
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
|
|
%l2 = load float, ptr %gep.a.iv.off, align 4
|
|
%ad = fadd fast float %l1, %l2
|
|
store float %ad, ptr %gep.a.iv, align 4
|
|
%gep.b = getelementptr inbounds float, ptr %b, i64 %iv
|
|
%gep.c = getelementptr inbounds float, ptr %c, i64 %iv2
|
|
%cmp = fcmp ult float %l1, 10.0
|
|
%select = select i1 %cmp, ptr %gep.b, ptr %gep.c
|
|
store float 0.0, ptr %select
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%iv2.next = add i64 %iv2, 2
|
|
%exitcond = icmp eq i64 %iv.next, %n
|
|
br i1 %exitcond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|