Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/NVPTX/reserved-smem-offset.ll
T
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

41 lines
1.8 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc < %s -mtriple=nvptx64-nvidia-cuda -mcpu=sm_80 -mattr=+ptx76 | FileCheck %s
; RUN: %if ptxas-sm_80 && ptxas-isa-7.6 %{ llc < %s -mtriple=nvptx64-nvidia-cuda -mcpu=sm_80 -mattr=+ptx76 | %ptxas-verify -arch=sm_80 %}
declare i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_begin()
declare i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_end()
declare i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_cap()
declare i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_0()
declare i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_1()
define i32 @test() {
; CHECK-LABEL: test(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<10>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: mov.u32 %r1, %reserved_smem_offset_begin;
; CHECK-NEXT: mov.u32 %r2, %reserved_smem_offset_end;
; CHECK-NEXT: mov.u32 %r3, %reserved_smem_offset_cap;
; CHECK-NEXT: mov.u32 %r4, %reserved_smem_offset_0;
; CHECK-NEXT: mov.u32 %r5, %reserved_smem_offset_1;
; CHECK-NEXT: add.s32 %r6, %r1, %r2;
; CHECK-NEXT: add.s32 %r7, %r6, %r3;
; CHECK-NEXT: add.s32 %r8, %r7, %r4;
; CHECK-NEXT: add.s32 %r9, %r8, %r5;
; CHECK-NEXT: st.param.b32 [func_retval0], %r9;
; CHECK-NEXT: ret;
%begin = call i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_begin()
%end = call i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_end()
%cap = call i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_cap()
%offset0 = call i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_0()
%offset1 = call i32 @llvm.nvvm.read.ptx.sreg.reserved_smem_offset_1()
%ret0 = add i32 %begin, %end
%ret1 = add i32 %ret0, %cap
%ret2 = add i32 %ret1, %offset0
%ret3 = add i32 %ret2, %offset1
ret i32 %ret3
}