Files
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

79 lines
3.1 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_32 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_32 | %ptxas-verify %}
declare float @llvm.nvvm.atomic.load.add.f32.p0(ptr %addr, float %val)
; CHECK-LABEL: atomic_add_f32_generic
define float @atomic_add_f32_generic(ptr %addr, float %val) {
; CHECK-LABEL: atomic_add_f32_generic(
; CHECK: {
; CHECK-NEXT: .reg .pred %p<2>;
; CHECK-NEXT: .reg .b32 %r<5>;
; CHECK-NEXT: .reg .b64 %rd<2>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r2, [atomic_add_f32_generic_param_1];
; CHECK-NEXT: ld.param.b64 %rd1, [atomic_add_f32_generic_param_0];
; CHECK-NEXT: ld.volatile.b32 %r4, [%rd1];
; CHECK-NEXT: $L__BB0_1: // %atomicrmw.start
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: add.rn.f32 %r3, %r4, %r2;
; CHECK-NEXT: atom.cas.b32 %r1, [%rd1], %r4, %r3;
; CHECK-NEXT: setp.ne.b32 %p1, %r1, %r4;
; CHECK-NEXT: mov.b32 %r4, %r1;
; CHECK-NEXT: @%p1 bra $L__BB0_1;
; CHECK-NEXT: // %bb.2: // %atomicrmw.end
; CHECK-NEXT: st.param.b32 [func_retval0], %r1;
; CHECK-NEXT: ret;
%ret = call float @llvm.nvvm.atomic.load.add.f32.p0(ptr %addr, float %val)
ret float %ret
}
declare float @llvm.nvvm.atomic.load.add.f32.p1(ptr addrspace(1) %addr, float %val)
; CHECK-LABEL: atomic_add_f32_addrspace1
define float @atomic_add_f32_addrspace1(ptr addrspace(1) %addr, float %val) {
; CHECK-LABEL: atomic_add_f32_addrspace1(
; CHECK: {
; CHECK-NEXT: .reg .pred %p<2>;
; CHECK-NEXT: .reg .b32 %r<5>;
; CHECK-NEXT: .reg .b64 %rd<2>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r2, [atomic_add_f32_addrspace1_param_1];
; CHECK-NEXT: ld.param.b64 %rd1, [atomic_add_f32_addrspace1_param_0];
; CHECK-NEXT: ld.volatile.global.b32 %r4, [%rd1];
; CHECK-NEXT: $L__BB1_1: // %atomicrmw.start
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: add.rn.f32 %r3, %r4, %r2;
; CHECK-NEXT: atom.global.cas.b32 %r1, [%rd1], %r4, %r3;
; CHECK-NEXT: setp.ne.b32 %p1, %r1, %r4;
; CHECK-NEXT: mov.b32 %r4, %r1;
; CHECK-NEXT: @%p1 bra $L__BB1_1;
; CHECK-NEXT: // %bb.2: // %atomicrmw.end
; CHECK-NEXT: st.param.b32 [func_retval0], %r1;
; CHECK-NEXT: ret;
%ret = call float @llvm.nvvm.atomic.load.add.f32.p1(ptr addrspace(1) %addr, float %val)
ret float %ret
}
declare float @llvm.nvvm.atomic.load.add.f32.p3(ptr addrspace(3) %addr, float %val)
; CHECK-LABEL: atomic_add_f32_addrspace3
define float @atomic_add_f32_addrspace3(ptr addrspace(3) %addr, float %val) {
; CHECK-LABEL: atomic_add_f32_addrspace3(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<3>;
; CHECK-NEXT: .reg .b64 %rd<2>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [atomic_add_f32_addrspace3_param_0];
; CHECK-NEXT: ld.param.b32 %r1, [atomic_add_f32_addrspace3_param_1];
; CHECK-NEXT: atom.shared.add.f32 %r2, [%rd1], %r1;
; CHECK-NEXT: st.param.b32 [func_retval0], %r2;
; CHECK-NEXT: ret;
%ret = call float @llvm.nvvm.atomic.load.add.f32.p3(ptr addrspace(3) %addr, float %val)
ret float %ret
}