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
68 lines
3.7 KiB
C
68 lines
3.7 KiB
C
//===-- sync-ops.h - --===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file implements outline macros for the __sync_fetch_and_*
|
|
// operations. Different instantiations will generate appropriate assembly for
|
|
// ARM and Thumb-2 versions of the functions.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "../assembly.h"
|
|
|
|
#if __ARM_ARCH >= 7
|
|
#define DMB dmb
|
|
#elif __ARM_ARCH >= 6
|
|
#define DMB mcr p15, #0, r0, c7, c10, #5
|
|
#else
|
|
#error DMB is only supported on ARMv6+
|
|
#endif
|
|
|
|
#define SYNC_OP_4(op) \
|
|
.p2align 2; \
|
|
.syntax unified; \
|
|
DEFINE_COMPILERRT_FUNCTION(__sync_fetch_and_##op) \
|
|
DMB; \
|
|
mov r12, r0; \
|
|
LOCAL_LABEL(tryatomic_##op) : ldrex r0, [r12]; \
|
|
op(r2, r0, r1); \
|
|
strex r3, r2, [r12]; \
|
|
cmp r3, #0; \
|
|
bne LOCAL_LABEL(tryatomic_##op); \
|
|
DMB; \
|
|
bx lr
|
|
|
|
#define SYNC_OP_8(op) \
|
|
.p2align 2; \
|
|
.syntax unified; \
|
|
DEFINE_COMPILERRT_FUNCTION(__sync_fetch_and_##op) \
|
|
push {r4, r5, r6, lr}; \
|
|
DMB; \
|
|
mov r12, r0; \
|
|
LOCAL_LABEL(tryatomic_##op) : ldrexd r0, r1, [r12]; \
|
|
op(r4, r5, r0, r1, r2, r3); \
|
|
strexd r6, r4, r5, [r12]; \
|
|
cmp r6, #0; \
|
|
bne LOCAL_LABEL(tryatomic_##op); \
|
|
DMB; \
|
|
pop { r4, r5, r6, pc }
|
|
|
|
#define MINMAX_4(rD, rN, rM, cmp_kind) \
|
|
cmp rN, rM; \
|
|
mov rD, rM; \
|
|
it cmp_kind; \
|
|
mov##cmp_kind rD, rN
|
|
|
|
#define MINMAX_8(rD_LO, rD_HI, rN_LO, rN_HI, rM_LO, rM_HI, cmp_kind) \
|
|
cmp rN_LO, rM_LO; \
|
|
sbcs rN_HI, rM_HI; \
|
|
mov rD_LO, rM_LO; \
|
|
mov rD_HI, rM_HI; \
|
|
itt cmp_kind; \
|
|
mov##cmp_kind rD_LO, rN_LO; \
|
|
mov##cmp_kind rD_HI, rN_HI
|