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
74 lines
4.1 KiB
LLVM
74 lines
4.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
|
|
; In PR41658, argpromotion put an inalloca in a position that per the
|
|
; calling convention is passed in a register. This test verifies that
|
|
; we don't do that anymore. It also verifies that the combination of
|
|
; globalopt and argpromotion is able to optimize the call safely.
|
|
;
|
|
; RUN: opt -S -passes=argpromotion %s | FileCheck %s --check-prefix=ARGPROMOTION
|
|
; RUN: opt -S -passes=globalopt,argpromotion %s | FileCheck %s --check-prefix=GLOBALOPT_ARGPROMOTION
|
|
|
|
target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
|
|
target triple = "i386-pc-windows-msvc19.11.0"
|
|
|
|
%struct.a = type { i8 }
|
|
|
|
define internal x86_thiscallcc void @internalfun(ptr %this, ptr inalloca(<{ %struct.a }>)) {
|
|
; ARGPROMOTION-LABEL: define {{[^@]+}}@internalfun
|
|
; ARGPROMOTION-SAME: (ptr [[THIS:%.*]], ptr inalloca(<{ [[STRUCT_A:%.*]] }>) [[TMP0:%.*]]) {
|
|
; ARGPROMOTION-NEXT: entry:
|
|
; ARGPROMOTION-NEXT: [[A:%.*]] = getelementptr inbounds <{ [[STRUCT_A]] }>, ptr [[TMP0]], i32 0, i32 0
|
|
; ARGPROMOTION-NEXT: [[ARGMEM:%.*]] = alloca inalloca <{ [[STRUCT_A]] }>, align 4
|
|
; ARGPROMOTION-NEXT: [[TMP1:%.*]] = getelementptr inbounds <{ [[STRUCT_A]] }>, ptr [[ARGMEM]], i32 0, i32 0
|
|
; ARGPROMOTION-NEXT: [[CALL:%.*]] = call x86_thiscallcc ptr @copy_ctor(ptr [[TMP1]], ptr dereferenceable(1) [[A]])
|
|
; ARGPROMOTION-NEXT: call void @ext(ptr inalloca(<{ [[STRUCT_A]] }>) [[ARGMEM]])
|
|
; ARGPROMOTION-NEXT: ret void
|
|
;
|
|
; GLOBALOPT_ARGPROMOTION-LABEL: define {{[^@]+}}@internalfun
|
|
; GLOBALOPT_ARGPROMOTION-SAME: (ptr [[TMP0:%.*]]) unnamed_addr {
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: entry:
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: [[A:%.*]] = getelementptr inbounds <{ [[STRUCT_A:%.*]] }>, ptr [[TMP0]], i32 0, i32 0
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: [[ARGMEM:%.*]] = alloca inalloca <{ [[STRUCT_A]] }>, align 4
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: [[TMP1:%.*]] = getelementptr inbounds <{ [[STRUCT_A]] }>, ptr [[ARGMEM]], i32 0, i32 0
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: [[CALL:%.*]] = call x86_thiscallcc ptr @copy_ctor(ptr [[TMP1]], ptr dereferenceable(1) [[A]])
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: call void @ext(ptr inalloca(<{ [[STRUCT_A]] }>) [[ARGMEM]])
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = getelementptr inbounds <{ %struct.a }>, ptr %0, i32 0, i32 0
|
|
%argmem = alloca inalloca <{ %struct.a }>, align 4
|
|
%1 = getelementptr inbounds <{ %struct.a }>, ptr %argmem, i32 0, i32 0
|
|
%call = call x86_thiscallcc ptr @copy_ctor(ptr %1, ptr dereferenceable(1) %a)
|
|
call void @ext(ptr inalloca(<{ %struct.a }>) %argmem)
|
|
ret void
|
|
}
|
|
|
|
; This is here to ensure @internalfun is live.
|
|
define void @exportedfun(ptr %a) {
|
|
; ARGPROMOTION-LABEL: define {{[^@]+}}@exportedfun
|
|
; ARGPROMOTION-SAME: (ptr [[A:%.*]]) {
|
|
; ARGPROMOTION-NEXT: [[INALLOCA_SAVE:%.*]] = tail call ptr @llvm.stacksave.p0()
|
|
; ARGPROMOTION-NEXT: [[ARGMEM:%.*]] = alloca inalloca <{ [[STRUCT_A:%.*]] }>, align 4
|
|
; ARGPROMOTION-NEXT: call x86_thiscallcc void @internalfun(ptr [[A]], ptr inalloca(<{ [[STRUCT_A]] }>) [[ARGMEM]])
|
|
; ARGPROMOTION-NEXT: call void @llvm.stackrestore.p0(ptr [[INALLOCA_SAVE]])
|
|
; ARGPROMOTION-NEXT: ret void
|
|
;
|
|
; GLOBALOPT_ARGPROMOTION-LABEL: define {{[^@]+}}@exportedfun
|
|
; GLOBALOPT_ARGPROMOTION-SAME: (ptr [[A:%.*]]) local_unnamed_addr {
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: [[INALLOCA_SAVE:%.*]] = tail call ptr @llvm.stacksave.p0()
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: [[ARGMEM:%.*]] = alloca inalloca <{ [[STRUCT_A:%.*]] }>, align 4
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: call fastcc void @internalfun(ptr [[ARGMEM]])
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: call void @llvm.stackrestore.p0(ptr [[INALLOCA_SAVE]])
|
|
; GLOBALOPT_ARGPROMOTION-NEXT: ret void
|
|
;
|
|
%inalloca.save = tail call ptr @llvm.stacksave()
|
|
%argmem = alloca inalloca <{ %struct.a }>, align 4
|
|
call x86_thiscallcc void @internalfun(ptr %a, ptr inalloca(<{ %struct.a }>) %argmem)
|
|
call void @llvm.stackrestore(ptr %inalloca.save)
|
|
ret void
|
|
}
|
|
|
|
declare x86_thiscallcc ptr @copy_ctor(ptr returned, ptr dereferenceable(1))
|
|
declare void @ext(ptr inalloca(<{ %struct.a }>))
|
|
declare ptr @llvm.stacksave()
|
|
declare void @llvm.stackrestore(ptr)
|