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
71 lines
2.3 KiB
LLVM
71 lines
2.3 KiB
LLVM
; RUN: opt -passes="module(print<block-freq>),function(loop(loop-idiom)),module(print<block-freq>)" -mtriple=x86_64 -mcpu=core-avx2 %s -disable-output 2>&1 | FileCheck --check-prefix=PROFILE %s
|
|
|
|
declare void @escape_inner(i8, i8, i8, i1, i8)
|
|
declare void @escape_outer(i8, i8, i8, i1, i8)
|
|
|
|
declare i8 @gen.i8()
|
|
|
|
; Most basic pattern; Note that iff the shift amount is offset, said offsetting
|
|
; must not cause an overflow, but `add nsw` is fine.
|
|
define i8 @p0(i8 %val, i8 %start, i8 %extraoffset) mustprogress {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i8 [ %start, %entry ], [ %iv.next, %loop ]
|
|
%nbits = add nsw i8 %iv, %extraoffset
|
|
%val.shifted = ashr i8 %val, %nbits
|
|
%val.shifted.iszero = icmp eq i8 %val.shifted, 0
|
|
%iv.next = add i8 %iv, 1
|
|
|
|
call void @escape_inner(i8 %iv, i8 %nbits, i8 %val.shifted, i1 %val.shifted.iszero, i8 %iv.next)
|
|
|
|
br i1 %val.shifted.iszero, label %end, label %loop, !prof !{!"branch_weights", i32 1, i32 1000 }
|
|
|
|
end:
|
|
%iv.res = phi i8 [ %iv, %loop ]
|
|
%nbits.res = phi i8 [ %nbits, %loop ]
|
|
%val.shifted.res = phi i8 [ %val.shifted, %loop ]
|
|
%val.shifted.iszero.res = phi i1 [ %val.shifted.iszero, %loop ]
|
|
%iv.next.res = phi i8 [ %iv.next, %loop ]
|
|
|
|
call void @escape_outer(i8 %iv.res, i8 %nbits.res, i8 %val.shifted.res, i1 %val.shifted.iszero.res, i8 %iv.next.res)
|
|
|
|
ret i8 %iv.res
|
|
}
|
|
|
|
define i32 @p1(i32 %x, i32 %bit) {
|
|
entry:
|
|
%bitmask = shl i32 1, %bit
|
|
br label %loop
|
|
|
|
loop:
|
|
%x.curr = phi i32 [ %x, %entry ], [ %x.next, %loop ]
|
|
%x.curr.bitmasked = and i32 %x.curr, %bitmask
|
|
%x.curr.isbitunset = icmp eq i32 %x.curr.bitmasked, 0
|
|
%x.next = shl i32 %x.curr, 1
|
|
br i1 %x.curr.isbitunset, label %loop, label %end, !prof !{!"branch_weights", i32 500, i32 1 }
|
|
|
|
end:
|
|
ret i32 %x.curr
|
|
}
|
|
|
|
;
|
|
; PROFILE: Printing analysis results of BFI for function 'p0':
|
|
; PROFILE: block-frequency-info: p0
|
|
; PROFILE: - entry: float = 1.0,
|
|
; PROFILE: - loop: float = 1001.0,
|
|
; PROFILE: - end: float = 1.0,
|
|
; PROFILE: block-frequency-info: p1
|
|
; PROFILE: - entry: float = 1.0,
|
|
; PROFILE: - loop: float = 501.0,
|
|
; PROFILE: - end: float = 1.0,
|
|
; PROFILE: block-frequency-info: p0
|
|
; PROFILE: - entry: float = 1.0,
|
|
; PROFILE: - loop: float = 1001.0,
|
|
; PROFILE: - end: float = 1.0,
|
|
; PROFILE: block-frequency-info: p1
|
|
; PROFILE: - entry: float = 1.0,
|
|
; PROFILE: - loop: float = 501.0,
|
|
; PROFILE: - end: float = 1.0,
|