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

60 lines
2.5 KiB
LLVM

; RUN: llc < %s -O0 -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -O0 -mtriple=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
; CHECK-LABEL: .visible .func callee(
; CHECK-NEXT: .param .align 16 .b8 callee_param_0[16],
; CHECK-NEXT: .param .align 16 .b8 callee_param_1[16],
define void @callee(i128, i128, ptr) {
; CHECK-DAG: ld.param.v2.b64 {%[[REG0:rd[0-9]+]], %[[REG1:rd[0-9]+]]}, [callee_param_0];
; CHECK-DAG: ld.param.v2.b64 {%[[REG2:rd[0-9]+]], %[[REG3:rd[0-9]+]]}, [callee_param_1];
; CHECK: mul.lo.s64 %[[REG4:rd[0-9]+]], %[[REG0]], %[[REG3]];
; CHECK-NEXT: mul.hi.u64 %[[REG5:rd[0-9]+]], %[[REG0]], %[[REG2]];
; CHECK-NEXT: add.s64 %[[REG6:rd[0-9]+]], %[[REG5]], %[[REG4]];
; CHECK-NEXT: mul.lo.s64 %[[REG7:rd[0-9]+]], %[[REG1]], %[[REG2]];
; CHECK-NEXT: add.s64 %[[REG8:rd[0-9]+]], %[[REG6]], %[[REG7]];
; CHECK-NEXT: mul.lo.s64 %[[REG9:rd[0-9]+]], %[[REG0]], %[[REG2]];
%a = mul i128 %0, %1
store i128 %a, ptr %2
ret void
}
; CHECK-LABEL: .visible .entry caller_kernel(
; CHECK-NEXT: .param .align 16 .b8 caller_kernel_param_0[16],
; CHECK-NEXT: .param .align 16 .b8 caller_kernel_param_1[16],
define ptx_kernel void @caller_kernel(i128, i128, ptr) {
start:
; CHECK-DAG: ld.param.v2.b64 {%[[REG0:rd[0-9]+]], %[[REG1:rd[0-9]+]]}, [caller_kernel_param_0];
; CHECK-DAG: ld.param.v2.b64 {%[[REG2:rd[0-9]+]], %[[REG3:rd[0-9]+]]}, [caller_kernel_param_1];
; CHECK: { // callseq [[CALLSEQ_ID:[0-9]]], 0
; CHECK-DAG: .param .align 16 .b8 param0[16];
; CHECK-DAG: .param .align 16 .b8 param1[16];
; CHECK-DAG: st.param.v2.b64 [param0], {%[[REG0]], %[[REG1]]}
; CHECK-DAG: st.param.v2.b64 [param1], {%[[REG2]], %[[REG3]]}
; CHECK: } // callseq [[CALLSEQ_ID]]
call void @callee(i128 %0, i128 %1, ptr %2)
ret void
}
; CHECK-LABEL: .visible .func caller_func(
; CHECK-NEXT: .param .align 16 .b8 caller_func_param_0[16],
; CHECK-NEXT: .param .align 16 .b8 caller_func_param_1[16],
define void @caller_func(i128, i128, ptr) {
start:
; CHECK-DAG: ld.param.v2.b64 {%[[REG0:rd[0-9]+]], %[[REG1:rd[0-9]+]]}, [caller_func_param_0]
; CHECK-DAG: ld.param.v2.b64 {%[[REG2:rd[0-9]+]], %[[REG3:rd[0-9]+]]}, [caller_func_param_1]
; CHECK: { // callseq [[CALLSEQ_ID:[0-9]]], 0
; CHECK-DAG: .param .align 16 .b8 param0[16];
; CHECK-DAG: .param .align 16 .b8 param1[16];
; CHECK-DAG: st.param.v2.b64 [param0], {%[[REG0]], %[[REG1]]}
; CHECK-DAG: st.param.v2.b64 [param1], {%[[REG2]], %[[REG3]]}
; CHECK: } // callseq [[CALLSEQ_ID]]
call void @callee(i128 %0, i128 %1, ptr %2)
ret void
}