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
52 lines
1.6 KiB
LLVM
52 lines
1.6 KiB
LLVM
; REQUIRES: asserts
|
|
; RUN: opt -passes=inline -mtriple=aarch64--linux-gnu -mcpu=kryo -S -debug-only=inline-cost < %s 2>&1 | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64--linux-gnu"
|
|
|
|
define void @outer1(ptr %ptr, i32 %i) {
|
|
call void @inner1(ptr %ptr, i32 %i)
|
|
ret void
|
|
}
|
|
|
|
define void @outer2(ptr %ptr, i32 %i) {
|
|
call void @inner2(ptr %ptr, i32 %i)
|
|
ret void
|
|
}
|
|
|
|
define void @outer3(ptr %ptr, i32 %j) {
|
|
call void @inner3(ptr %ptr, i32 0, i32 %j)
|
|
ret void
|
|
}
|
|
|
|
; The gep in inner1() is reg+reg, which is a legal addressing mode for AArch64.
|
|
; Thus, both the gep and ret can be simplified.
|
|
; CHECK: Analyzing call of inner1
|
|
; CHECK: NumInstructionsSimplified: 2
|
|
; CHECK: NumInstructions: 2
|
|
define void @inner1(ptr %ptr, i32 %i) {
|
|
%G = getelementptr inbounds [4 x i32], ptr %ptr, i32 0, i32 %i
|
|
ret void
|
|
}
|
|
|
|
; The gep in inner2() is reg+imm+reg, which is not a legal addressing mode for
|
|
; AArch64. Thus, only the ret can be simplified and not the gep.
|
|
; CHECK: Analyzing call of inner2
|
|
; CHECK: NumInstructionsSimplified: 1
|
|
; CHECK: NumInstructions: 2
|
|
define void @inner2(ptr %ptr, i32 %i) {
|
|
%G = getelementptr inbounds [4 x i32], ptr %ptr, i32 1, i32 %i
|
|
ret void
|
|
}
|
|
|
|
; The gep in inner3() is reg+reg because %i is a known constant from the
|
|
; callsite. This case is a legal addressing mode for AArch64. Thus, both the
|
|
; gep and ret can be simplified.
|
|
; CHECK: Analyzing call of inner3
|
|
; CHECK: NumInstructionsSimplified: 2
|
|
; CHECK: NumInstructions: 2
|
|
define void @inner3(ptr %ptr, i32 %i, i32 %j) {
|
|
%G = getelementptr inbounds [4 x i32], ptr %ptr, i32 %i, i32 %j
|
|
ret void
|
|
}
|