f62c379f71
This commit adds NVPTX codegen support for clusterlaunchcontrol instructions with tests under clusterlaunchcontrol.ll and clusterlaunchcontrol-multicast.ll. For more information, Please refer [PTX ISA](https://docs.nvidia.com/cuda/parallel-thread-execution/?a#parallel-synchronization-and-communication-instructions-clusterlaunchcontrol-try-cancel)
43 lines
3.3 KiB
LLVM
43 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -o - -mcpu=sm_100a -march=nvptx64 -mattr=+ptx86 %s | FileCheck %s --check-prefixes=CHECK,CHECK-PTX-SHARED64
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
|
|
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 | %ptxas-verify -arch=sm_100a %}
|
|
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_100a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_100a %}
|
|
; RUN: llc -o - -mcpu=sm_101a -march=nvptx64 -mattr=+ptx86 %s | FileCheck %s --check-prefixes=CHECK,CHECK-PTX-SHARED64
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
|
|
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 | %ptxas-verify -arch=sm_101a %}
|
|
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_101a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_101a %}
|
|
; RUN: llc -o - -mcpu=sm_120a -march=nvptx64 -mattr=+ptx86 %s | FileCheck %s --check-prefixes=CHECK,CHECK-PTX-SHARED64
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 --nvptx-short-ptr | FileCheck --check-prefixes=CHECK,CHECK-PTX-SHARED32 %s
|
|
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 | %ptxas-verify -arch=sm_120a %}
|
|
; RUN: %if ptxas-12.8 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_120a -mattr=+ptx86 --nvptx-short-ptr | %ptxas-verify -arch=sm_120a %}
|
|
|
|
define void @nvvm_clusterlaunchcontrol_try_cancel_multicast(
|
|
; CHECK-PTX-SHARED64-LABEL: nvvm_clusterlaunchcontrol_try_cancel_multicast(
|
|
; CHECK-PTX-SHARED64: {
|
|
; CHECK-PTX-SHARED64-NEXT: .reg .b64 %rd<3>;
|
|
; CHECK-PTX-SHARED64-EMPTY:
|
|
; CHECK-PTX-SHARED64-NEXT: // %bb.0:
|
|
; CHECK-PTX-SHARED64-NEXT: ld.param.b64 %rd1, [nvvm_clusterlaunchcontrol_try_cancel_multicast_param_0];
|
|
; CHECK-PTX-SHARED64-NEXT: ld.param.b64 %rd2, [nvvm_clusterlaunchcontrol_try_cancel_multicast_param_1];
|
|
; CHECK-PTX-SHARED64-NEXT: clusterlaunchcontrol.try_cancel.async.shared::cta.mbarrier::complete_tx::bytes.multicast::cluster::all.b128 [%rd1], [%rd2];
|
|
; CHECK-PTX-SHARED64-NEXT: ret;
|
|
;
|
|
; CHECK-PTX-SHARED32-LABEL: nvvm_clusterlaunchcontrol_try_cancel_multicast(
|
|
; CHECK-PTX-SHARED32: {
|
|
; CHECK-PTX-SHARED32-NEXT: .reg .b32 %r<3>;
|
|
; CHECK-PTX-SHARED32-EMPTY:
|
|
; CHECK-PTX-SHARED32-NEXT: // %bb.0:
|
|
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r1, [nvvm_clusterlaunchcontrol_try_cancel_multicast_param_0];
|
|
; CHECK-PTX-SHARED32-NEXT: ld.param.b32 %r2, [nvvm_clusterlaunchcontrol_try_cancel_multicast_param_1];
|
|
; CHECK-PTX-SHARED32-NEXT: clusterlaunchcontrol.try_cancel.async.shared::cta.mbarrier::complete_tx::bytes.multicast::cluster::all.b128 [%r1], [%r2];
|
|
; CHECK-PTX-SHARED32-NEXT: ret;
|
|
ptr addrspace(3) %saddr, ptr addrspace(3) %smbar,
|
|
i128 %try_cancel_response) {
|
|
|
|
tail call void @llvm.nvvm.clusterlaunchcontrol.try_cancel.async.multicast.shared(ptr addrspace(3) %saddr, ptr addrspace(3) %smbar)
|
|
ret void;
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; CHECK: {{.*}}
|