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
168 lines
5.9 KiB
LLVM
168 lines
5.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=aarch64 -sink-insts-to-avoid-spills | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
|
|
@A = external dso_local global [100 x i32], align 4
|
|
|
|
define i32 @sink_load_and_copy(i32 %n) {
|
|
; CHECK-LABEL: sink_load_and_copy:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w20, -16
|
|
; CHECK-NEXT: .cfi_offset w21, -24
|
|
; CHECK-NEXT: .cfi_offset w30, -32
|
|
; CHECK-NEXT: mov w19, w0
|
|
; CHECK-NEXT: cmp w0, #1
|
|
; CHECK-NEXT: b.lt .LBB0_3
|
|
; CHECK-NEXT: // %bb.1: // %for.body.preheader
|
|
; CHECK-NEXT: adrp x8, A
|
|
; CHECK-NEXT: mov w21, w19
|
|
; CHECK-NEXT: ldr w20, [x8, :lo12:A]
|
|
; CHECK-NEXT: .LBB0_2: // %for.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: mov w0, w20
|
|
; CHECK-NEXT: bl _Z3usei
|
|
; CHECK-NEXT: sdiv w19, w19, w0
|
|
; CHECK-NEXT: subs w21, w21, #1
|
|
; CHECK-NEXT: b.ne .LBB0_2
|
|
; CHECK-NEXT: .LBB0_3: // %for.cond.cleanup
|
|
; CHECK-NEXT: mov w0, w19
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp x30, x21, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%cmp63 = icmp sgt i32 %n, 0
|
|
br i1 %cmp63, label %for.body.preheader, label %for.cond.cleanup
|
|
|
|
for.body.preheader:
|
|
%0 = load i32, ptr @A, align 4
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
%sum.0.lcssa = phi i32 [ %n, %entry ], [ %div, %for.body ]
|
|
ret i32 %sum.0.lcssa
|
|
|
|
for.body:
|
|
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
|
|
%sum.065 = phi i32 [ %div, %for.body ], [ %n, %for.body.preheader ]
|
|
%call = tail call i32 @_Z3usei(i32 %0)
|
|
%div = sdiv i32 %sum.065, %call
|
|
%lsr.iv.next = add i32 %lsr.iv, -1
|
|
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
|
|
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
|
|
}
|
|
|
|
define i32 @cant_sink_successive_call(i32 %n) {
|
|
; CHECK-LABEL: cant_sink_successive_call:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w20, -16
|
|
; CHECK-NEXT: .cfi_offset w21, -24
|
|
; CHECK-NEXT: .cfi_offset w30, -32
|
|
; CHECK-NEXT: mov w19, w0
|
|
; CHECK-NEXT: cmp w0, #1
|
|
; CHECK-NEXT: b.lt .LBB1_3
|
|
; CHECK-NEXT: // %bb.1: // %for.body.preheader
|
|
; CHECK-NEXT: adrp x8, A
|
|
; CHECK-NEXT: mov w0, w19
|
|
; CHECK-NEXT: ldr w20, [x8, :lo12:A]
|
|
; CHECK-NEXT: bl _Z3usei
|
|
; CHECK-NEXT: mov w21, w19
|
|
; CHECK-NEXT: .LBB1_2: // %for.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: mov w0, w20
|
|
; CHECK-NEXT: bl _Z3usei
|
|
; CHECK-NEXT: sdiv w19, w19, w0
|
|
; CHECK-NEXT: subs w21, w21, #1
|
|
; CHECK-NEXT: b.ne .LBB1_2
|
|
; CHECK-NEXT: .LBB1_3: // %for.cond.cleanup
|
|
; CHECK-NEXT: mov w0, w19
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp x30, x21, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%cmp63 = icmp sgt i32 %n, 0
|
|
br i1 %cmp63, label %for.body.preheader, label %for.cond.cleanup
|
|
|
|
for.body.preheader:
|
|
%0 = load i32, ptr @A, align 4
|
|
%call0 = tail call i32 @_Z3usei(i32 %n)
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
%sum.0.lcssa = phi i32 [ %n, %entry ], [ %div, %for.body ]
|
|
ret i32 %sum.0.lcssa
|
|
|
|
for.body:
|
|
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
|
|
%sum.065 = phi i32 [ %div, %for.body ], [ %n, %for.body.preheader ]
|
|
%call = tail call i32 @_Z3usei(i32 %0)
|
|
%div = sdiv i32 %sum.065, %call
|
|
%lsr.iv.next = add i32 %lsr.iv, -1
|
|
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
|
|
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
|
|
}
|
|
|
|
define i32 @cant_sink_successive_store(ptr nocapture readnone %store, i32 %n) {
|
|
; CHECK-LABEL: cant_sink_successive_store:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w20, -16
|
|
; CHECK-NEXT: .cfi_offset w21, -24
|
|
; CHECK-NEXT: .cfi_offset w30, -32
|
|
; CHECK-NEXT: mov w19, w1
|
|
; CHECK-NEXT: cmp w1, #1
|
|
; CHECK-NEXT: b.lt .LBB2_3
|
|
; CHECK-NEXT: // %bb.1: // %for.body.preheader
|
|
; CHECK-NEXT: adrp x8, A
|
|
; CHECK-NEXT: mov w21, w19
|
|
; CHECK-NEXT: ldr w20, [x8, :lo12:A]
|
|
; CHECK-NEXT: mov w8, #42 // =0x2a
|
|
; CHECK-NEXT: str w8, [x0]
|
|
; CHECK-NEXT: .LBB2_2: // %for.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: mov w0, w20
|
|
; CHECK-NEXT: bl _Z3usei
|
|
; CHECK-NEXT: sdiv w19, w19, w0
|
|
; CHECK-NEXT: subs w21, w21, #1
|
|
; CHECK-NEXT: b.ne .LBB2_2
|
|
; CHECK-NEXT: .LBB2_3: // %for.cond.cleanup
|
|
; CHECK-NEXT: mov w0, w19
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp x30, x21, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%cmp63 = icmp sgt i32 %n, 0
|
|
br i1 %cmp63, label %for.body.preheader, label %for.cond.cleanup
|
|
|
|
for.body.preheader:
|
|
%0 = load i32, ptr @A, align 4
|
|
store i32 42, ptr %store, align 4
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
%sum.0.lcssa = phi i32 [ %n, %entry ], [ %div, %for.body ]
|
|
ret i32 %sum.0.lcssa
|
|
|
|
for.body:
|
|
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
|
|
%sum.065 = phi i32 [ %div, %for.body ], [ %n, %for.body.preheader ]
|
|
%call = tail call i32 @_Z3usei(i32 %0)
|
|
%div = sdiv i32 %sum.065, %call
|
|
%lsr.iv.next = add i32 %lsr.iv, -1
|
|
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
|
|
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
|
|
}
|
|
|
|
declare i32 @_Z3usei(i32)
|