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
105 lines
3.3 KiB
LLVM
105 lines
3.3 KiB
LLVM
; RUN: llc < %s -mtriple=arm-linux -mcpu=generic -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=ARM
|
|
; RUN: llc < %s -mtriple=thumbv6m-eabi -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=THUMBV6
|
|
; RUN: llc < %s -mtriple=thumbv7-eabi -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=THUMBV7
|
|
|
|
define i32 @uadd_overflow(i32 %a, i32 %b) #0 {
|
|
%sadd = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
|
|
%1 = extractvalue { i32, i1 } %sadd, 1
|
|
%2 = zext i1 %1 to i32
|
|
ret i32 %2
|
|
|
|
; CHECK-LABEL: uadd_overflow:
|
|
|
|
; ARM: adds r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
|
|
; ARM: mov r[[R2:[0-9]+]], #0
|
|
; ARM: adc r[[R0]], r[[R2]], #0
|
|
|
|
; THUMBV6: movs r[[R2:[0-9]+]], #0
|
|
; THUMBV6: adds r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
|
|
; THUMBV6: adcs r[[R2]], r[[R2]]
|
|
; THUMBV6: mov r[[R0]], r[[R2]]
|
|
|
|
; THUMBV7: adds r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
|
|
; THUMBV7: mov.w r[[R2:[0-9]+]], #0
|
|
; THUMBV7: adc r[[R0]], r[[R2]], #0
|
|
}
|
|
|
|
|
|
define i32 @sadd_overflow(i32 %a, i32 %b) #0 {
|
|
%sadd = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
|
|
%1 = extractvalue { i32, i1 } %sadd, 1
|
|
%2 = zext i1 %1 to i32
|
|
ret i32 %2
|
|
|
|
; CHECK-LABEL: sadd_overflow:
|
|
|
|
; ARM: adds r[[R2:[0-9]+]], r[[R0:[0-9]+]], r[[R1:[0-9]+]]
|
|
; ARM: mov r[[R0]], #1
|
|
; ARM: movvc r[[R0]], #0
|
|
; ARM: mov pc, lr
|
|
|
|
; THUMBV6: adds r0, r0, r1
|
|
; THUMBV6: bvc .LBB1_2
|
|
|
|
; THUMBV7: adds r[[R2:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
|
|
; THUMBV7: mov.w r[[R0:[0-9]+]], #1
|
|
; THUMBV7: it vc
|
|
; THUMBV7: movvc r[[R0]], #0
|
|
}
|
|
|
|
define i32 @usub_overflow(i32 %a, i32 %b) #0 {
|
|
%sadd = tail call { i32, i1 } @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
|
|
%1 = extractvalue { i32, i1 } %sadd, 1
|
|
%2 = zext i1 %1 to i32
|
|
ret i32 %2
|
|
|
|
; CHECK-LABEL: usub_overflow:
|
|
|
|
; ARM: subs r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
|
|
; ARM: mov r[[R2:[0-9]+]], #0
|
|
; ARM: adc r[[R0]], r[[R2]], #0
|
|
; ARM: eor r[[R0]], r[[R0]], #1
|
|
|
|
; THUMBV6: movs r[[R2:[0-9]+]], #0
|
|
; THUMBV6: subs r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
|
|
; THUMBV6: adcs r[[R2]], r[[R2]]
|
|
; THUMBV6: movs r[[R0]], #1
|
|
; THUMBV6: eors r[[R0]], r[[R2]]
|
|
|
|
; THUMBV7: subs r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
|
|
; THUMBV7: mov.w r[[R2:[0-9]+]], #0
|
|
; THUMBV7: adc r[[R0]], r[[R2]], #0
|
|
; THUMBV7: eor r[[R0]], r[[R0]], #1
|
|
|
|
; We should know that the overflow is just 1 bit,
|
|
; no need to clear any other bit
|
|
; CHECK-NOT: and
|
|
}
|
|
|
|
define i32 @ssub_overflow(i32 %a, i32 %b) #0 {
|
|
%sadd = tail call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
|
|
%1 = extractvalue { i32, i1 } %sadd, 1
|
|
%2 = zext i1 %1 to i32
|
|
ret i32 %2
|
|
|
|
; CHECK-LABEL: ssub_overflow:
|
|
|
|
; ARM: mov r[[R2]], #1
|
|
; ARM: cmp r[[R0]], r[[R1]]
|
|
; ARM: movvc r[[R2]], #0
|
|
|
|
; THUMBV6: cmp r0, r1
|
|
; THUMBV6: bvc .LBB3_2
|
|
|
|
; THUMBV7: movs r[[R2:[0-9]+]], #1
|
|
; THUMBV7: cmp r[[R0:[0-9]+]], r[[R1:[0-9]+]]
|
|
; THUMBV7: it vc
|
|
; THUMBV7: movvc r[[R2]], #0
|
|
; THUMBV7: mov r[[R0]], r[[R2]]
|
|
}
|
|
|
|
declare { i32, i1 } @llvm.uadd.with.overflow.i32(i32, i32) #1
|
|
declare { i32, i1 } @llvm.sadd.with.overflow.i32(i32, i32) #2
|
|
declare { i32, i1 } @llvm.usub.with.overflow.i32(i32, i32) #3
|
|
declare { i32, i1 } @llvm.ssub.with.overflow.i32(i32, i32) #4
|