[AMDGPU][Attributor] Add AAAMDGPUClusterDims
#158076
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This stack of pull requests is managed by Graphite. Learn more about stacking. |
|
@llvm/pr-subscribers-backend-amdgpu Author: Shilei Tian (shiltian) ChangesPatch is 160.84 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/158076.diff 27 Files Affected:
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAttributes.def b/llvm/lib/Target/AMDGPU/AMDGPUAttributes.def
index 8c1c8219690ba..4c9715e4a1737 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAttributes.def
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAttributes.def
@@ -31,5 +31,8 @@ AMDGPU_ATTRIBUTE(LDS_KERNEL_ID, "amdgpu-no-lds-kernel-id")
AMDGPU_ATTRIBUTE(DEFAULT_QUEUE, "amdgpu-no-default-queue")
AMDGPU_ATTRIBUTE(COMPLETION_ACTION, "amdgpu-no-completion-action")
AMDGPU_ATTRIBUTE(FLAT_SCRATCH_INIT, "amdgpu-no-flat-scratch-init")
+AMDGPU_ATTRIBUTE(CLUSTER_ID_X, "amdgpu-no-cluster-id-x")
+AMDGPU_ATTRIBUTE(CLUSTER_ID_Y, "amdgpu-no-cluster-id-y")
+AMDGPU_ATTRIBUTE(CLUSTER_ID_Z, "amdgpu-no-cluster-id-z")
#undef AMDGPU_ATTRIBUTE
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
index f646457f9d76f..49f87513777f1 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
@@ -77,6 +77,13 @@ intrinsicToAttrMask(Intrinsic::ID ID, bool &NonKernelOnly, bool &NeedsImplicit,
case Intrinsic::amdgcn_workgroup_id_z:
case Intrinsic::r600_read_tgid_z:
return WORKGROUP_ID_Z;
+ case Intrinsic::amdgcn_cluster_id_x:
+ NonKernelOnly = true;
+ return CLUSTER_ID_X;
+ case Intrinsic::amdgcn_cluster_id_y:
+ return CLUSTER_ID_Y;
+ case Intrinsic::amdgcn_cluster_id_z:
+ return CLUSTER_ID_Z;
case Intrinsic::amdgcn_lds_kernel_id:
return LDS_KERNEL_ID;
case Intrinsic::amdgcn_dispatch_ptr:
@@ -1296,6 +1303,157 @@ struct AAAMDGPUNoAGPR
const char AAAMDGPUNoAGPR::ID = 0;
+/// An abstract attribute to propagate the function attribute
+/// "amdgpu-cluster-dims" from kernel entry functions to device functions.
+struct AAAMDGPUClusterDims
+ : public StateWrapper<BooleanState, AbstractAttribute> {
+ using Base = StateWrapper<BooleanState, AbstractAttribute>;
+ AAAMDGPUClusterDims(const IRPosition &IRP, Attributor &A) : Base(IRP) {}
+
+ /// Create an abstract attribute view for the position \p IRP.
+ static AAAMDGPUClusterDims &createForPosition(const IRPosition &IRP,
+ Attributor &A);
+
+ /// See AbstractAttribute::getName().
+ StringRef getName() const override { return "AAAMDGPUClusterDims"; }
+
+ /// See AbstractAttribute::getIdAddr().
+ const char *getIdAddr() const override { return &ID; }
+
+ /// This function should return true if the type of the \p AA is
+ /// AAAMDGPUClusterDims.
+ static bool classof(const AbstractAttribute *AA) {
+ return (AA->getIdAddr() == &ID);
+ }
+
+ virtual const AMDGPU::ClusterDimsAttr &getClusterDims() const = 0;
+
+ /// Unique ID (due to the unique address)
+ static const char ID;
+};
+
+const char AAAMDGPUClusterDims::ID = 0;
+
+struct AAAMDGPUClusterDimsFunction : public AAAMDGPUClusterDims {
+ AAAMDGPUClusterDimsFunction(const IRPosition &IRP, Attributor &A)
+ : AAAMDGPUClusterDims(IRP, A) {}
+
+ void initialize(Attributor &A) override {
+ Function *F = getAssociatedFunction();
+ assert(F && "empty associated function");
+
+ Attr = AMDGPU::ClusterDimsAttr::get(*F);
+
+ // No matter what a kernel function has, it is final.
+ if (AMDGPU::isEntryFunctionCC(F->getCallingConv())) {
+ if (Attr.isUnknown())
+ indicatePessimisticFixpoint();
+ else
+ indicateOptimisticFixpoint();
+ }
+ }
+
+ const std::string getAsStr(Attributor *A) const override {
+ if (!getAssumed() || Attr.isUnknown())
+ return "unknown";
+ if (Attr.isNoCluster())
+ return "no";
+ if (Attr.isVariableedDims())
+ return "variable";
+ return Attr.to_string();
+ }
+
+ void trackStatistics() const override {}
+
+ ChangeStatus updateImpl(Attributor &A) override {
+ auto OldState = Attr;
+
+ auto CheckCallSite = [&](AbstractCallSite CS) {
+ const auto *CallerAA = A.getAAFor<AAAMDGPUClusterDims>(
+ *this, IRPosition::function(*CS.getInstruction()->getFunction()),
+ DepClassTy::REQUIRED);
+ if (!CallerAA || !CallerAA->isValidState())
+ return false;
+
+ return merge(CallerAA->getClusterDims());
+ };
+
+ bool UsedAssumedInformation = false;
+ if (!A.checkForAllCallSites(CheckCallSite, *this,
+ /*RequireAllCallSites=*/true,
+ UsedAssumedInformation))
+ return indicatePessimisticFixpoint();
+
+ return OldState == Attr ? ChangeStatus::UNCHANGED : ChangeStatus::CHANGED;
+ }
+
+ ChangeStatus manifest(Attributor &A) override {
+ if (Attr.isUnknown())
+ return ChangeStatus::UNCHANGED;
+ return A.manifestAttrs(
+ getIRPosition(),
+ {Attribute::get(getAssociatedFunction()->getContext(), AttrName,
+ Attr.to_string())},
+ /*ForceReplace=*/true);
+ }
+
+ const AMDGPU::ClusterDimsAttr &getClusterDims() const override {
+ return Attr;
+ }
+
+private:
+ bool merge(const AMDGPU::ClusterDimsAttr &Other) {
+ // Case 1: Both of them are unknown yet, we do nothing and continue wait for
+ // propagation.
+ if (Attr.isUnknown() && Other.isUnknown())
+ return true;
+
+ // Case 2: The other is determined, but we are unknown yet, we simply take
+ // the other's value.
+ if (Attr.isUnknown()) {
+ Attr = Other;
+ return true;
+ }
+
+ // Case 3: We are determined but the other is unknown yet, we simply keep
+ // everything unchanged.
+ if (Other.isUnknown())
+ return true;
+
+ // After this point, both are determined.
+
+ // Case 4: If they are same, we do nothing.
+ if (Attr == Other)
+ return true;
+
+ // Now they are not same.
+
+ // Case 5: If either of us uses cluster (but not both; otherwise case 4
+ // would hold), then it is unknown whether cluster will be used, and the
+ // state is final, unlike case 1.
+ if (Attr.isNoCluster() || Other.isNoCluster()) {
+ Attr.setUnknown();
+ return false;
+ }
+
+ // Case 6: Both of us use cluster, but the dims are different, so the result
+ // is, cluster is used, but we just don't have a fixed dims.
+ Attr.setVariableDims();
+ return true;
+ }
+
+ AMDGPU::ClusterDimsAttr Attr;
+
+ static constexpr const char AttrName[] = "amdgpu-cluster-dims";
+};
+
+AAAMDGPUClusterDims &
+AAAMDGPUClusterDims::createForPosition(const IRPosition &IRP, Attributor &A) {
+ if (IRP.getPositionKind() == IRPosition::IRP_FUNCTION)
+ return *new (A.Allocator) AAAMDGPUClusterDimsFunction(IRP, A);
+ llvm_unreachable("AAAMDGPUClusterDims is only valid for function position");
+}
+
static bool runImpl(Module &M, AnalysisGetter &AG, TargetMachine &TM,
AMDGPUAttributorOptions Options,
ThinOrFullLTOPhase LTOPhase) {
@@ -1314,7 +1472,7 @@ static bool runImpl(Module &M, AnalysisGetter &AG, TargetMachine &TM,
&AAAMDMaxNumWorkgroups::ID, &AAAMDWavesPerEU::ID, &AAAMDGPUNoAGPR::ID,
&AACallEdges::ID, &AAPointerInfo::ID, &AAPotentialConstantValues::ID,
&AAUnderlyingObjects::ID, &AANoAliasAddrSpace::ID, &AAAddressSpace::ID,
- &AAIndirectCallInfo::ID});
+ &AAIndirectCallInfo::ID, &AAAMDGPUClusterDims::ID});
AttributorConfig AC(CGUpdater);
AC.IsClosedWorldModule = Options.IsClosedWorld;
@@ -1352,6 +1510,10 @@ static bool runImpl(Module &M, AnalysisGetter &AG, TargetMachine &TM,
A.getOrCreateAAFor<AAAMDWavesPerEU>(IRPosition::function(*F));
}
+ const GCNSubtarget &ST = TM.getSubtarget<GCNSubtarget>(*F);
+ if (!F->isDeclaration() && ST.hasClusters())
+ A.getOrCreateAAFor<AAAMDGPUClusterDims>(IRPosition::function(*F));
+
for (auto &I : instructions(F)) {
Value *Ptr = nullptr;
if (auto *LI = dyn_cast<LoadInst>(&I))
diff --git a/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll b/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll
index 42c7b90da63d3..2d7ef2c262157 100644
--- a/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll
+++ b/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll
@@ -169,6 +169,6 @@ attributes #1 = { nounwind }
;.
; HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
-; HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-cluster-id-x" "amdgpu-no-cluster-id-y" "amdgpu-no-cluster-id-z" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-cluster-id-x" "amdgpu-no-cluster-id-y" "amdgpu-no-cluster-id-z" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
;.
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-attributor-no-agpr.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-attributor-no-agpr.ll
index 7e9cb7adf4fc2..664dfa21759cf 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-attributor-no-agpr.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-attributor-no-agpr.ll
@@ -254,9 +254,9 @@ define amdgpu_kernel void @indirect_calls_none_agpr(i1 %cond) {
attributes #0 = { "amdgpu-agpr-alloc"="0" }
;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx90a" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR1]] = { "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx90a" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR2]] = { "target-cpu"="gfx90a" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-cluster-id-x" "amdgpu-no-cluster-id-y" "amdgpu-no-cluster-id-z" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx90a" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { "amdgpu-agpr-alloc"="0" "amdgpu-no-cluster-id-x" "amdgpu-no-cluster-id-y" "amdgpu-no-cluster-id-z" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx90a" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR2:[0-9]+]] = { "target-cpu"="gfx90a" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR3:[0-9]+]] = { convergent nocallback nofree nosync nounwind willreturn memory(none) "target-cpu"="gfx90a" }
; CHECK: attributes #[[ATTR4:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) "target-cpu"="gfx90a" }
; CHECK: attributes #[[ATTR5:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) "target-cpu"="gfx90a" }
diff --git a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll
index 7f7bbb2a95902..a688b6fc6399f 100644
--- a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll
+++ b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll
@@ -691,29 +691,29 @@ attributes #6 = { "enqueued-block" }
;.
; ATTRIBUTOR_HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
-; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-gr...
[truncated]
|
shiltian
force-pushed
the
users/shiltian/cluster-dimds-attributor
branch
from
7774114 to
b78e877
Compare
shiltian
force-pushed
the
users/shiltian/cluster-intrinsics-lowering
branch
from
ebb1152 to
f33ec0a
Compare
arsenm
reviewed
Sep 11, 2025
rampitec
approved these changes
Sep 11, 2025
shiltian
force-pushed
the
users/shiltian/cluster-intrinsics-lowering
branch
from
f33ec0a to
6c2e110
Compare
shiltian
force-pushed
the
users/shiltian/cluster-dimds-attributor
branch
3 times, most recently
from
b8ae788 to
e1ca0a1
Compare
shiltian
force-pushed
the
users/shiltian/cluster-intrinsics-lowering
branch
5 times, most recently
from
1ba5764 to
661ad40
Compare
Base automatically changed from
users/shiltian/cluster-intrinsics-lowering
to
main
September 13, 2025 01:11
shiltian
force-pushed
the
users/shiltian/cluster-dimds-attributor
branch
from
e1ca0a1 to
8fc95f7
Compare
shiltian
force-pushed
the
users/shiltian/cluster-dimds-attributor
branch
from
8fc95f7 to
86cccb5
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.