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
82 lines
3.5 KiB
LLVM
82 lines
3.5 KiB
LLVM
; RUN: opt -verify-loop-info -passes=irce -S < %s | FileCheck %s
|
|
; RUN: opt -verify-loop-info -passes='require<branch-prob>,irce' -S < %s | FileCheck %s
|
|
|
|
define void @single_access_with_preloop(ptr %arr, ptr %a_len_ptr, i32 %n, i32 %offset) {
|
|
entry:
|
|
%len = load i32, ptr %a_len_ptr, !range !0
|
|
%first.itr.check = icmp sgt i32 %n, 0
|
|
br i1 %first.itr.check, label %loop, label %exit
|
|
|
|
loop:
|
|
%idx = phi i32 [ 0, %entry ] , [ %idx.next, %in.bounds ]
|
|
%idx.next = add i32 %idx, 1
|
|
%array.idx = add i32 %idx, %offset
|
|
%abc.high = icmp slt i32 %array.idx, %len
|
|
%abc.low = icmp sge i32 %array.idx, 0
|
|
%abc = and i1 %abc.low, %abc.high
|
|
br i1 %abc, label %in.bounds, label %out.of.bounds, !prof !1
|
|
|
|
in.bounds:
|
|
%addr = getelementptr i32, ptr %arr, i32 %array.idx
|
|
store i32 0, ptr %addr
|
|
%next = icmp slt i32 %idx.next, %n
|
|
br i1 %next, label %loop, label %exit
|
|
|
|
out.of.bounds:
|
|
ret void
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @single_access_with_preloop(
|
|
; CHECK: loop.preheader:
|
|
; CHECK: [[safe_offset_preloop:[^ ]+]] = call i32 @llvm.smax.i32(i32 %offset, i32 -2147483647)
|
|
; If Offset was a SINT_MIN, we could have an overflow here. That is why we calculated its safe version.
|
|
; CHECK: [[safe_start:[^ ]+]] = sub i32 0, [[safe_offset_preloop]]
|
|
; CHECK: [[exit_preloop_at_loclamp:[^ ]+]] = call i32 @llvm.smin.i32(i32 %n, i32 [[safe_start]])
|
|
; CHECK: [[exit_preloop_at:[^ ]+]] = call i32 @llvm.smax.i32(i32 [[exit_preloop_at_loclamp]], i32 0)
|
|
|
|
|
|
; CHECK: [[len_minus_sint_max:[^ ]+]] = add nuw nsw i32 %len, -2147483647
|
|
; CHECK: [[safe_offset_mainloop:[^ ]+]] = call i32 @llvm.smax.i32(i32 %offset, i32 [[len_minus_sint_max]])
|
|
; If Offset was a SINT_MIN, we could have an overflow here. That is why we calculated its safe version.
|
|
; CHECK: [[safe_upper_end:[^ ]+]] = sub i32 %len, [[safe_offset_mainloop]]
|
|
; CHECK: [[exit_mainloop_at_loclamp:[^ ]+]] = call i32 @llvm.smin.i32(i32 %n, i32 [[safe_upper_end]])
|
|
; CHECK: [[safe_offset_mainloop_2:[^ ]+]] = call i32 @llvm.smax.i32(i32 %offset, i32 0)
|
|
; CHECK: [[safe_lower_end:[^ ]+]] = sub i32 2147483647, [[safe_offset_mainloop_2]]
|
|
; CHECK: [[exit_mainloop_at_hiclamp:[^ ]+]] = call i32 @llvm.smin.i32(i32 [[exit_mainloop_at_loclamp]], i32 [[safe_lower_end]])
|
|
; CHECK: [[exit_mainloop_at:[^ ]+]] = call i32 @llvm.smax.i32(i32 [[exit_mainloop_at_hiclamp]], i32 0)
|
|
|
|
; CHECK: mainloop:
|
|
; CHECK: br label %loop
|
|
|
|
; CHECK: loop:
|
|
; CHECK: %abc.high = icmp slt i32 %array.idx, %len
|
|
; CHECK: %abc.low = icmp sge i32 %array.idx, 0
|
|
; CHECK: %abc = and i1 true, true
|
|
; CHECK: br i1 %abc, label %in.bounds, label %[[loopexit:[^ ,]+]]
|
|
|
|
; CHECK: in.bounds:
|
|
; CHECK: [[continue_mainloop_cond:[^ ]+]] = icmp slt i32 %idx.next, [[exit_mainloop_at]]
|
|
; CHECK: br i1 [[continue_mainloop_cond]], label %loop, label %main.exit.selector
|
|
|
|
; CHECK: main.exit.selector:
|
|
; CHECK: [[mainloop_its_left:[^ ]+]] = icmp slt i32 %idx.next.lcssa, %n
|
|
; CHECK: br i1 [[mainloop_its_left]], label %main.pseudo.exit, label %exit.loopexit
|
|
|
|
; CHECK: in.bounds.preloop:
|
|
; CHECK: [[continue_preloop_cond:[^ ]+]] = icmp slt i32 %idx.next.preloop, [[exit_preloop_at]]
|
|
; CHECK: br i1 [[continue_preloop_cond]], label %loop.preloop, label %preloop.exit.selector
|
|
|
|
; CHECK: preloop.exit.selector:
|
|
; CHECK: [[preloop_its_left:[^ ]+]] = icmp slt i32 %idx.next.preloop.lcssa, %n
|
|
; CHECK: br i1 [[preloop_its_left]], label %preloop.pseudo.exit, label %exit.loopexit
|
|
|
|
; CHECK: in.bounds.postloop:
|
|
; CHECK: %next.postloop = icmp slt i32 %idx.next.postloop, %n
|
|
; CHECK: br i1 %next.postloop, label %loop.postloop, label %exit.loopexit
|
|
|
|
!0 = !{i32 0, i32 2147483647}
|
|
!1 = !{!"branch_weights", i32 64, i32 4}
|