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
67 lines
2.2 KiB
LLVM
67 lines
2.2 KiB
LLVM
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | FileCheck %s
|
|
; RUN: %if ptxas-sm_80 && ptxas-isa-7.0 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_80 -mattr=+ptx70 | %ptxas-verify -arch=sm_80 %}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.umin(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_min_u32
|
|
define i32 @redux_sync_min_u32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.min.u32
|
|
%val = call i32 @llvm.nvvm.redux.sync.umin(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.umax(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_max_u32
|
|
define i32 @redux_sync_max_u32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.max.u32
|
|
%val = call i32 @llvm.nvvm.redux.sync.umax(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.add(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_add_s32
|
|
define i32 @redux_sync_add_s32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.add.s32
|
|
%val = call i32 @llvm.nvvm.redux.sync.add(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.min(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_min_s32
|
|
define i32 @redux_sync_min_s32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.min.s32
|
|
%val = call i32 @llvm.nvvm.redux.sync.min(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.max(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_max_s32
|
|
define i32 @redux_sync_max_s32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.max.s32
|
|
%val = call i32 @llvm.nvvm.redux.sync.max(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.and(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_and_b32
|
|
define i32 @redux_sync_and_b32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.and.b32
|
|
%val = call i32 @llvm.nvvm.redux.sync.and(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.xor(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_xor_b32
|
|
define i32 @redux_sync_xor_b32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.xor.b32
|
|
%val = call i32 @llvm.nvvm.redux.sync.xor(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|
|
|
|
declare i32 @llvm.nvvm.redux.sync.or(i32, i32)
|
|
; CHECK-LABEL: .func{{.*}}redux_sync_or_b32
|
|
define i32 @redux_sync_or_b32(i32 %src, i32 %mask) {
|
|
; CHECK: redux.sync.or.b32
|
|
%val = call i32 @llvm.nvvm.redux.sync.or(i32 %src, i32 %mask)
|
|
ret i32 %val
|
|
}
|