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
454 lines
12 KiB
LLVM
454 lines
12 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: opt -mtriple=aarch64-unknown-linux-gnu -mattr=+sme -S -passes=inline < %s | FileCheck %s
|
|
|
|
declare void @inlined_body()
|
|
|
|
;
|
|
; Define some functions that will be called by the functions below.
|
|
; These just call a '...body()' function. If we see the call to one of
|
|
; these functions being replaced by '...body()', then we know it has been
|
|
; inlined.
|
|
;
|
|
|
|
define void @nonza_callee() {
|
|
; CHECK-LABEL: define void @nonza_callee
|
|
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void asm sideeffect "; inlineasm", ""()
|
|
call void @inlined_body()
|
|
ret void
|
|
}
|
|
|
|
define void @shared_za_callee() "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_callee
|
|
; CHECK-SAME: () #[[ATTR1:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void asm sideeffect "; inlineasm", ""()
|
|
call void @inlined_body()
|
|
ret void
|
|
}
|
|
|
|
define void @new_za_callee() "aarch64_new_za" {
|
|
; CHECK-LABEL: define void @new_za_callee
|
|
; CHECK-SAME: () #[[ATTR2:[0-9]+]] {
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void asm sideeffect "; inlineasm", ""()
|
|
call void @inlined_body()
|
|
ret void
|
|
}
|
|
|
|
define void @agnostic_za_callee() "aarch64_za_state_agnostic" {
|
|
; CHECK-LABEL: define void @agnostic_za_callee
|
|
; CHECK-SAME: () #[[ATTR3:[0-9]+]] {
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void asm sideeffect "; inlineasm", ""()
|
|
call void @inlined_body()
|
|
ret void
|
|
}
|
|
|
|
;
|
|
; Now test that inlining only happens when no lazy-save is needed.
|
|
; Test for a number of combinations, where:
|
|
; N Not using ZA.
|
|
; S Shared ZA interface
|
|
; Z New ZA with Private-ZA interface
|
|
; A Agnostic ZA interface
|
|
|
|
; [x] N -> N
|
|
; [ ] N -> S (This combination is invalid)
|
|
; [ ] N -> Z
|
|
; [ ] N -> A
|
|
define void @nonza_caller_nonza_callee_inline() {
|
|
; CHECK-LABEL: define void @nonza_caller_nonza_callee_inline
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @nonza_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] N -> N
|
|
; [ ] N -> S (This combination is invalid)
|
|
; [x] N -> Z
|
|
; [ ] N -> A
|
|
define void @nonza_caller_new_za_callee_dont_inline() {
|
|
; CHECK-LABEL: define void @nonza_caller_new_za_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @new_za_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @new_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] N -> N
|
|
; [ ] N -> S (This combination is invalid)
|
|
; [ ] N -> Z
|
|
; [x] N -> A
|
|
define void @nonza_caller_agnostic_za_callee_inline() {
|
|
; CHECK-LABEL: define void @nonza_caller_agnostic_za_callee_inline
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @agnostic_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [x] Z -> N
|
|
; [ ] Z -> S
|
|
; [ ] Z -> Z
|
|
; [ ] Z -> A
|
|
define void @new_za_caller_nonza_callee_dont_inline() "aarch64_new_za" {
|
|
; CHECK-LABEL: define void @new_za_caller_nonza_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR2]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @nonza_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @nonza_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] Z -> N
|
|
; [x] Z -> S
|
|
; [ ] Z -> Z
|
|
; [ ] Z -> A
|
|
define void @new_za_caller_shared_za_callee_inline() "aarch64_new_za" {
|
|
; CHECK-LABEL: define void @new_za_caller_shared_za_callee_inline
|
|
; CHECK-SAME: () #[[ATTR2]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @shared_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] Z -> N
|
|
; [ ] Z -> S
|
|
; [x] Z -> Z
|
|
; [ ] Z -> A
|
|
define void @new_za_caller_new_za_callee_dont_inline() "aarch64_new_za" {
|
|
; CHECK-LABEL: define void @new_za_caller_new_za_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR2]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @new_za_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @new_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] Z -> N
|
|
; [ ] Z -> S
|
|
; [ ] Z -> Z
|
|
; [x] Z -> A
|
|
define void @new_za_caller_agnostic_za_callee_inline() "aarch64_new_za" {
|
|
; CHECK-LABEL: define void @new_za_caller_agnostic_za_callee_inline
|
|
; CHECK-SAME: () #[[ATTR2]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @agnostic_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [x] S -> N
|
|
; [ ] S -> S
|
|
; [ ] S -> Z
|
|
; [ ] S -> A
|
|
define void @shared_za_caller_nonza_callee_dont_inline() "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_caller_nonza_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR1]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @nonza_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @nonza_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] S -> N
|
|
; [x] S -> Z
|
|
; [ ] S -> S
|
|
; [ ] S -> A
|
|
define void @shared_za_caller_new_za_callee_dont_inline() "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_caller_new_za_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR1]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @new_za_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @new_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] S -> N
|
|
; [ ] S -> Z
|
|
; [x] S -> S
|
|
; [ ] S -> A
|
|
define void @shared_za_caller_shared_za_callee_inline() "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_caller_shared_za_callee_inline
|
|
; CHECK-SAME: () #[[ATTR1]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @shared_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] S -> N
|
|
; [ ] S -> Z
|
|
; [ ] S -> S
|
|
; [x] S -> A
|
|
define void @shared_za_caller_agnostic_za_callee_inline() "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_caller_agnostic_za_callee_inline
|
|
; CHECK-SAME: () #[[ATTR1]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @agnostic_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [x] A -> N
|
|
; [ ] A -> Z
|
|
; [ ] A -> S
|
|
; [ ] A -> A
|
|
define void @agnostic_za_caller_nonza_callee_dont_inline() "aarch64_za_state_agnostic" {
|
|
; CHECK-LABEL: define void @agnostic_za_caller_nonza_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR3]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @nonza_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @nonza_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] A -> N
|
|
; [x] A -> Z
|
|
; [ ] A -> S
|
|
; [ ] A -> A
|
|
define void @agnostic_za_caller_new_za_callee_dont_inline() "aarch64_za_state_agnostic" {
|
|
; CHECK-LABEL: define void @agnostic_za_caller_new_za_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR3]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @new_za_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @new_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] A -> N
|
|
; [ ] A -> Z
|
|
; [x] A -> S (invalid)
|
|
; [ ] A -> A
|
|
define void @agnostic_za_caller_shared_za_callee_dont_inline() "aarch64_za_state_agnostic" {
|
|
; CHECK-LABEL: define void @agnostic_za_caller_shared_za_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR3]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @shared_za_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @shared_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; [ ] A -> N
|
|
; [ ] A -> Z
|
|
; [ ] A -> S
|
|
; [x] A -> A
|
|
define void @agnostic_za_caller_agnostic_za_callee_inline() "aarch64_za_state_agnostic" {
|
|
; CHECK-LABEL: define void @agnostic_za_caller_agnostic_za_callee_inline
|
|
; CHECK-SAME: () #[[ATTR3]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @agnostic_za_callee()
|
|
ret void
|
|
}
|
|
|
|
|
|
|
|
define void @private_za_callee_call_za_disable() {
|
|
; CHECK-LABEL: define void @private_za_callee_call_za_disable
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: call void @__arm_za_disable()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @__arm_za_disable()
|
|
ret void
|
|
}
|
|
|
|
define void @shared_za_caller_private_za_callee_call_za_disable() "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_caller_private_za_callee_call_za_disable
|
|
; CHECK-SAME: () #[[ATTR1]] {
|
|
; CHECK-NEXT: call void @private_za_callee_call_za_disable()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @private_za_callee_call_za_disable()
|
|
ret void
|
|
}
|
|
|
|
define void @private_za_callee_call_tpidr2_save() {
|
|
; CHECK-LABEL: define void @private_za_callee_call_tpidr2_save
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: call void @__arm_tpidr2_save()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @__arm_tpidr2_save()
|
|
ret void
|
|
}
|
|
|
|
define void @shared_za_caller_private_za_callee_call_tpidr2_save_dont_inline() "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_caller_private_za_callee_call_tpidr2_save_dont_inline
|
|
; CHECK-SAME: () #[[ATTR1]] {
|
|
; CHECK-NEXT: call void @private_za_callee_call_tpidr2_save()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @private_za_callee_call_tpidr2_save()
|
|
ret void
|
|
}
|
|
|
|
define void @private_za_callee_call_tpidr2_restore(ptr %ptr) {
|
|
; CHECK-LABEL: define void @private_za_callee_call_tpidr2_restore
|
|
; CHECK-SAME: (ptr [[PTR:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: call void @__arm_tpidr2_restore(ptr [[PTR]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @__arm_tpidr2_restore(ptr %ptr)
|
|
ret void
|
|
}
|
|
|
|
define void @shared_za_caller_private_za_callee_call_tpidr2_restore_dont_inline(ptr %ptr) "aarch64_inout_za" {
|
|
; CHECK-LABEL: define void @shared_za_caller_private_za_callee_call_tpidr2_restore_dont_inline
|
|
; CHECK-SAME: (ptr [[PTR:%.*]]) #[[ATTR1]] {
|
|
; CHECK-NEXT: call void @private_za_callee_call_tpidr2_restore(ptr [[PTR]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @private_za_callee_call_tpidr2_restore(ptr %ptr)
|
|
ret void
|
|
}
|
|
|
|
define void @nonzt0_callee() {
|
|
; CHECK-LABEL: define void @nonzt0_callee
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void asm sideeffect "; inlineasm", ""()
|
|
call void @inlined_body()
|
|
ret void
|
|
}
|
|
|
|
define void @new_zt0_callee() "aarch64_new_zt0" {
|
|
; CHECK-LABEL: define void @new_zt0_callee
|
|
; CHECK-SAME: () #[[ATTR4:[0-9]+]] {
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void asm sideeffect "; inlineasm", ""()
|
|
call void @inlined_body()
|
|
ret void
|
|
}
|
|
|
|
define void @nonzt0_caller_new_zt0_callee_dont_inline() {
|
|
; CHECK-LABEL: define void @nonzt0_caller_new_zt0_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: call void @new_zt0_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
call void @new_zt0_callee()
|
|
ret void
|
|
}
|
|
|
|
define void @shared_zt0_caller_nonzt0_callee_dont_inline() "aarch64_inout_zt0" {
|
|
; CHECK-LABEL: define void @shared_zt0_caller_nonzt0_callee_dont_inline
|
|
; CHECK-SAME: () #[[ATTR5:[0-9]+]] {
|
|
; CHECK-NEXT: call void @nonzt0_callee()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @nonzt0_callee()
|
|
ret void
|
|
}
|
|
|
|
define void @shared_zt0_callee() "aarch64_inout_zt0" {
|
|
; CHECK-LABEL: define void @shared_zt0_callee
|
|
; CHECK-SAME: () #[[ATTR5]] {
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void asm sideeffect "; inlineasm", ""()
|
|
call void @inlined_body()
|
|
ret void
|
|
}
|
|
|
|
define void @shared_zt0_caller_shared_zt0_callee_inline() "aarch64_inout_zt0" {
|
|
; CHECK-LABEL: define void @shared_zt0_caller_shared_zt0_callee_inline
|
|
; CHECK-SAME: () #[[ATTR5]] {
|
|
; CHECK-NEXT: call void asm sideeffect "
|
|
; CHECK-NEXT: call void @inlined_body()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @shared_zt0_callee()
|
|
ret void
|
|
}
|
|
|
|
declare void @__arm_za_disable()
|
|
declare void @__arm_tpidr2_save()
|
|
declare void @__arm_tpidr2_restore(ptr)
|