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
288 lines
6.6 KiB
LLVM
288 lines
6.6 KiB
LLVM
; RUN: llc < %s -O0 -mtriple=x86_64-unknown-unknown -mcpu=corei7 -verify-machineinstrs -show-mc-encoding | FileCheck %s --check-prefix X64
|
|
; RUN: llc < %s -O0 -mtriple=i386-unknown-unknown -mcpu=corei7 -verify-machineinstrs | FileCheck %s --check-prefix X32
|
|
|
|
@sc16 = external dso_local global i16
|
|
@fsc16 = external dso_local global half
|
|
|
|
define void @atomic_fetch_add16() nounwind {
|
|
; X64-LABEL: atomic_fetch_add16
|
|
; X32-LABEL: atomic_fetch_add16
|
|
entry:
|
|
; 32-bit
|
|
%t1 = atomicrmw add ptr @sc16, i16 1 acquire
|
|
; X64: lock
|
|
; X64: incw
|
|
; X32: lock
|
|
; X32: incw
|
|
%t2 = atomicrmw add ptr @sc16, i16 3 acquire
|
|
; X64: lock
|
|
; X64: addw $3, {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: addw $3
|
|
%t3 = atomicrmw add ptr @sc16, i16 5 acquire
|
|
; X64: lock
|
|
; X64: xaddw {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: xaddw
|
|
%t4 = atomicrmw add ptr @sc16, i16 %t3 acquire
|
|
; X64: lock
|
|
; X64: addw {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: addw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_sub16() nounwind {
|
|
; X64-LABEL: atomic_fetch_sub16
|
|
; X32-LABEL: atomic_fetch_sub16
|
|
%t1 = atomicrmw sub ptr @sc16, i16 1 acquire
|
|
; X64: lock
|
|
; X64: decw
|
|
; X32: lock
|
|
; X32: decw
|
|
%t2 = atomicrmw sub ptr @sc16, i16 3 acquire
|
|
; X64: lock
|
|
; X64: subw $3, {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: subw $3
|
|
%t3 = atomicrmw sub ptr @sc16, i16 5 acquire
|
|
; X64: lock
|
|
; X64: xaddw {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: xaddw
|
|
%t4 = atomicrmw sub ptr @sc16, i16 %t3 acquire
|
|
; X64: lock
|
|
; X64: subw {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: subw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_and16() nounwind {
|
|
; X64-LABEL: atomic_fetch_and16
|
|
; X32-LABEL: atomic_fetch_and16
|
|
%t1 = atomicrmw and ptr @sc16, i16 3 acquire
|
|
; X64: lock
|
|
; X64: andw $3, {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: andw $3
|
|
%t2 = atomicrmw and ptr @sc16, i16 5 acquire
|
|
; X64: andl
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
; X32: andl
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
%t3 = atomicrmw and ptr @sc16, i16 %t2 acquire
|
|
; X64: lock
|
|
; X64: andw {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: andw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_or16() nounwind {
|
|
; X64-LABEL: atomic_fetch_or16
|
|
; X32-LABEL: atomic_fetch_or16
|
|
%t1 = atomicrmw or ptr @sc16, i16 3 acquire
|
|
; X64: lock
|
|
; X64: orw $3, {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: orw $3
|
|
%t2 = atomicrmw or ptr @sc16, i16 5 acquire
|
|
; X64: orl
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
; X32: orl
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
%t3 = atomicrmw or ptr @sc16, i16 %t2 acquire
|
|
; X64: lock
|
|
; X64: orw {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: orw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_xor16() nounwind {
|
|
; X64-LABEL: atomic_fetch_xor16
|
|
; X32-LABEL: atomic_fetch_xor16
|
|
%t1 = atomicrmw xor ptr @sc16, i16 3 acquire
|
|
; X64: lock
|
|
; X64: xorw $3, {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: xorw $3
|
|
%t2 = atomicrmw xor ptr @sc16, i16 5 acquire
|
|
; X64: xorl
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
; X32: xorl
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
%t3 = atomicrmw xor ptr @sc16, i16 %t2 acquire
|
|
; X64: lock
|
|
; X64: xorw {{.*}} # encoding: [0x66,0xf0
|
|
; X32: lock
|
|
; X32: xorw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_nand16(i16 %x) nounwind {
|
|
; X64-LABEL: atomic_fetch_nand16
|
|
; X32-LABEL: atomic_fetch_nand16
|
|
%t1 = atomicrmw nand ptr @sc16, i16 %x acquire
|
|
; X64: andl
|
|
; X64: notl
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
; X32: andl
|
|
; X32: notl
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_max16(i16 %x) nounwind {
|
|
; X64-LABEL: atomic_fetch_max16
|
|
; X32-LABEL: atomic_fetch_max16
|
|
%t1 = atomicrmw max ptr @sc16, i16 %x acquire
|
|
; X64: movw
|
|
; X64: movw
|
|
; X64: subw
|
|
; X64: cmov
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
|
|
; X32: movw
|
|
; X32: movw
|
|
; X32: subw
|
|
; X32: cmov
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_min16(i16 %x) nounwind {
|
|
; X64-LABEL: atomic_fetch_min16
|
|
; X32-LABEL: atomic_fetch_min16
|
|
%t1 = atomicrmw min ptr @sc16, i16 %x acquire
|
|
; X64: movw
|
|
; X64: movw
|
|
; X64: subw
|
|
; X64: cmov
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
|
|
; X32: movw
|
|
; X32: movw
|
|
; X32: subw
|
|
; X32: cmov
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_umax16(i16 %x) nounwind {
|
|
; X64-LABEL: atomic_fetch_umax16
|
|
; X32-LABEL: atomic_fetch_umax16
|
|
%t1 = atomicrmw umax ptr @sc16, i16 %x acquire
|
|
; X64: movw
|
|
; X64: movw
|
|
; X64: subw
|
|
; X64: cmov
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
|
|
; X32: movw
|
|
; X32: movw
|
|
; X32: subw
|
|
; X32: cmov
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_umin16(i16 %x) nounwind {
|
|
; X64-LABEL: atomic_fetch_umin16
|
|
; X32-LABEL: atomic_fetch_umin16
|
|
%t1 = atomicrmw umin ptr @sc16, i16 %x acquire
|
|
; X64: movw
|
|
; X64: movw
|
|
; X64: subw
|
|
; X64: cmov
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
|
|
; X32: movw
|
|
; X32: movw
|
|
; X32: subw
|
|
; X32: cmov
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_cmpxchg16() nounwind {
|
|
%t1 = cmpxchg ptr @sc16, i16 0, i16 1 acquire acquire
|
|
; X64: lock
|
|
; X64: cmpxchgw
|
|
; X32: lock
|
|
; X32: cmpxchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_store16(i16 %x) nounwind {
|
|
store atomic i16 %x, ptr @sc16 release, align 4
|
|
; X64-NOT: lock
|
|
; X64: movw
|
|
; X32-NOT: lock
|
|
; X32: movw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_swap16(i16 %x) nounwind {
|
|
%t1 = atomicrmw xchg ptr @sc16, i16 %x acquire
|
|
; X64-NOT: lock
|
|
; X64: xchgw
|
|
; X32-NOT: lock
|
|
; X32: xchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|
|
|
|
define void @atomic_fetch_swapf16(half %x) nounwind {
|
|
%t1 = atomicrmw xchg ptr @fsc16, half %x acquire
|
|
; X64-NOT: lock
|
|
; X64: xchgw
|
|
; X32-NOT: lock
|
|
; X32: xchgw
|
|
ret void
|
|
; X64: ret
|
|
; X32: ret
|
|
}
|