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
112 lines
3.5 KiB
LLVM
112 lines
3.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-unknown-linux"
|
|
|
|
; Check an "expensive" construction of a constant is hoisted out of a loop
|
|
define void @f0(ptr %a, i64 %n) {
|
|
; CHECK-LABEL: f0:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: str x30, [sp, #-48]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: stp x22, x21, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp x20, x19, [sp, #32] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w20, -16
|
|
; CHECK-NEXT: .cfi_offset w21, -24
|
|
; CHECK-NEXT: .cfi_offset w22, -32
|
|
; CHECK-NEXT: .cfi_offset w30, -48
|
|
; CHECK-NEXT: mov x21, #1 // =0x1
|
|
; CHECK-NEXT: mov x19, x1
|
|
; CHECK-NEXT: mov x20, x0
|
|
; CHECK-NEXT: movk x21, #22136, lsl #16
|
|
; CHECK-NEXT: mov x22, xzr
|
|
; CHECK-NEXT: movk x21, #4660, lsl #48
|
|
; CHECK-NEXT: cmp x22, x19
|
|
; CHECK-NEXT: b.ge .LBB0_2
|
|
; CHECK-NEXT: .LBB0_1: // %loop.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: ldr w0, [x20, x22, lsl #2]
|
|
; CHECK-NEXT: mov x1, x21
|
|
; CHECK-NEXT: bl g
|
|
; CHECK-NEXT: str w0, [x20, x22, lsl #2]
|
|
; CHECK-NEXT: add x22, x22, #1
|
|
; CHECK-NEXT: cmp x22, x19
|
|
; CHECK-NEXT: b.lt .LBB0_1
|
|
; CHECK-NEXT: .LBB0_2: // %exit
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #32] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp x22, x21, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldr x30, [sp], #48 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%i = phi i64 [0, %entry], [%i.next, %loop.body]
|
|
%c = icmp slt i64 %i, %n
|
|
br i1 %c, label %loop.body, label %exit
|
|
|
|
loop.body:
|
|
%p = getelementptr i32, ptr %a, i64 %i
|
|
%v = load i32, ptr %p
|
|
%w = call i32 @g(i32 %v, i64 1311673392922361857) ; 0x1234000056780001
|
|
store i32 %w, ptr %p
|
|
%i.next = add i64 %i, 1
|
|
br label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
; Check a "cheap" to construct constant is materialised inside a loop.
|
|
define void @f1(ptr %a, i64 %n) {
|
|
; CHECK-LABEL: f1:
|
|
; 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 x19, x1
|
|
; CHECK-NEXT: mov x20, x0
|
|
; CHECK-NEXT: mov x21, xzr
|
|
; CHECK-NEXT: cmp x21, x19
|
|
; CHECK-NEXT: b.ge .LBB1_2
|
|
; CHECK-NEXT: .LBB1_1: // %loop.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: ldr w0, [x20, x21, lsl #2]
|
|
; CHECK-NEXT: mov x1, #1450704896 // =0x56780000
|
|
; CHECK-NEXT: movk x1, #4660, lsl #48
|
|
; CHECK-NEXT: bl g
|
|
; CHECK-NEXT: str w0, [x20, x21, lsl #2]
|
|
; CHECK-NEXT: add x21, x21, #1
|
|
; CHECK-NEXT: cmp x21, x19
|
|
; CHECK-NEXT: b.lt .LBB1_1
|
|
; CHECK-NEXT: .LBB1_2: // %exit
|
|
; 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:
|
|
br label %loop
|
|
|
|
loop:
|
|
%i = phi i64 [0, %entry], [%i.next, %loop.body]
|
|
%c = icmp slt i64 %i, %n
|
|
br i1 %c, label %loop.body, label %exit
|
|
|
|
loop.body:
|
|
%p = getelementptr i32, ptr %a, i64 %i
|
|
%v = load i32, ptr %p
|
|
%w = call i32 @g(i32 %v, i64 1311673392922361856) ; 0x1234000056780000
|
|
store i32 %w, ptr %p
|
|
%i.next = add i64 %i, 1
|
|
br label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
declare i32 @g(i32, i64)
|