forked from OSchip/llvm-project
[Attributor] Change AAExecutionDomain to check intrinsic edges
The AAExecutionDomain instance checks if a BB is executed by the main thread only. Currently, this only checks the `__kmpc_kernel_init` call for generic regions to indicate the path taken by the main thread. In the new runtime, we want to be able to detect basic blocks even in SPMD mode. For this we enable it to check thread-ID intrinsics being compared to zero as well. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D109849
This commit is contained in:
parent
fec2927e07
commit
27905eeb89
|
@ -33,6 +33,8 @@
|
|||
#include "llvm/IR/GlobalValue.h"
|
||||
#include "llvm/IR/Instruction.h"
|
||||
#include "llvm/IR/IntrinsicInst.h"
|
||||
#include "llvm/IR/IntrinsicsAMDGPU.h"
|
||||
#include "llvm/IR/IntrinsicsNVPTX.h"
|
||||
#include "llvm/InitializePasses.h"
|
||||
#include "llvm/Support/CommandLine.h"
|
||||
#include "llvm/Transforms/IPO.h"
|
||||
|
@ -2554,9 +2556,8 @@ ChangeStatus AAExecutionDomainFunction::updateImpl(Attributor &A) {
|
|||
auto &OMPInfoCache = static_cast<OMPInformationCache &>(A.getInfoCache());
|
||||
auto &RFI = OMPInfoCache.RFIs[OMPRTL___kmpc_target_init];
|
||||
|
||||
// Check if the edge into the successor block compares the __kmpc_target_init
|
||||
// result with -1. If we are in non-SPMD-mode that signals only the main
|
||||
// thread will execute the edge.
|
||||
// Check if the edge into the successor block contains a condition that only
|
||||
// lets the main thread execute it.
|
||||
auto IsInitialThreadOnly = [&](BranchInst *Edge, BasicBlock *SuccessorBB) {
|
||||
if (!Edge || !Edge->isConditional())
|
||||
return false;
|
||||
|
@ -2571,7 +2572,7 @@ ChangeStatus AAExecutionDomainFunction::updateImpl(Attributor &A) {
|
|||
if (!C)
|
||||
return false;
|
||||
|
||||
// Match: -1 == __kmpc_target_init (for non-SPMD kernels only!)
|
||||
// Match: -1 == __kmpc_target_init (for non-SPMD kernels only!)
|
||||
if (C->isAllOnesValue()) {
|
||||
auto *CB = dyn_cast<CallBase>(Cmp->getOperand(0));
|
||||
CB = CB ? OpenMPOpt::getCallIfRegularCall(*CB, &RFI) : nullptr;
|
||||
|
@ -2583,6 +2584,18 @@ ChangeStatus AAExecutionDomainFunction::updateImpl(Attributor &A) {
|
|||
return IsSPMDModeCI && IsSPMDModeCI->isZero();
|
||||
}
|
||||
|
||||
if (C->isZero()) {
|
||||
// Match: 0 == llvm.nvvm.read.ptx.sreg.tid.x()
|
||||
if (auto *II = dyn_cast<IntrinsicInst>(Cmp->getOperand(0)))
|
||||
if (II->getIntrinsicID() == Intrinsic::nvvm_read_ptx_sreg_tid_x)
|
||||
return true;
|
||||
|
||||
// Match: 0 == llvm.amdgcn.workitem.id.x()
|
||||
if (auto *II = dyn_cast<IntrinsicInst>(Cmp->getOperand(0)))
|
||||
if (II->getIntrinsicID() == Intrinsic::amdgcn_workitem_id_x)
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
};
|
||||
|
||||
|
|
|
@ -18,8 +18,6 @@ define void @kernel() {
|
|||
%cmp = icmp eq i32 %call, -1
|
||||
br i1 %cmp, label %if.then, label %if.else
|
||||
if.then:
|
||||
call void @nvptx()
|
||||
call void @amdgcn()
|
||||
br label %if.end
|
||||
if.else:
|
||||
br label %if.end
|
||||
|
@ -31,13 +29,15 @@ if.end:
|
|||
; REMARKS: remark: single_threaded_execution.c:1:0: Could not internalize function. Some optimizations may not be possible.
|
||||
; REMARKS-NOT: remark: single_threaded_execution.c:1:0: Could not internalize function. Some optimizations may not be possible.
|
||||
|
||||
; CHECK-DAG: [openmp-opt] Basic block @nvptx entry is executed by a single thread.
|
||||
; CHECK-NOT: [openmp-opt] Basic block @nvptx entry is executed by a single thread.
|
||||
; CHECK-DAG: [openmp-opt] Basic block @nvptx if.then is executed by a single thread.
|
||||
; CHECK-DAG: [openmp-opt] Basic block @nvptx if.end is executed by a single thread.
|
||||
; CHECK-NOT: [openmp-opt] Basic block @nvptx if.end is executed by a single thread.
|
||||
; Function Attrs: noinline
|
||||
define internal void @nvptx() {
|
||||
define void @nvptx() {
|
||||
entry:
|
||||
br i1 true, label %if.then, label %if.end
|
||||
%call = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
|
||||
%cmp = icmp eq i32 %call, 0
|
||||
br i1 %cmp, label %if.then, label %if.end
|
||||
|
||||
if.then:
|
||||
call void @foo()
|
||||
|
@ -50,13 +50,15 @@ if.end:
|
|||
ret void
|
||||
}
|
||||
|
||||
; CHECK-DAG: [openmp-opt] Basic block @amdgcn entry is executed by a single thread.
|
||||
; CHECK-NOT: [openmp-opt] Basic block @amdgcn entry is executed by a single thread.
|
||||
; CHECK-DAG: [openmp-opt] Basic block @amdgcn if.then is executed by a single thread.
|
||||
; CHECK-DAG: [openmp-opt] Basic block @amdgcn if.end is executed by a single thread.
|
||||
; CHECK-NOT: [openmp-opt] Basic block @amdgcn if.end is executed by a single thread.
|
||||
; Function Attrs: noinline
|
||||
define internal void @amdgcn() {
|
||||
define void @amdgcn() {
|
||||
entry:
|
||||
br i1 false, label %if.then, label %if.end
|
||||
%call = call i32 @llvm.amdgcn.workitem.id.x()
|
||||
%cmp = icmp eq i32 %call, 0
|
||||
br i1 %cmp, label %if.then, label %if.end
|
||||
|
||||
if.then:
|
||||
call void @foo()
|
||||
|
@ -104,6 +106,7 @@ declare i32 @llvm.amdgcn.workitem.id.x()
|
|||
declare void @__kmpc_kernel_prepare_parallel(i8*)
|
||||
|
||||
declare i32 @__kmpc_target_init(%struct.ident_t*, i1, i1, i1)
|
||||
|
||||
declare void @__kmpc_target_deinit(%struct.ident_t*, i1, i1)
|
||||
|
||||
attributes #0 = { cold noinline }
|
||||
|
|
Loading…
Reference in New Issue