[llvm] [LoopVectorizer] Prune VFs based on plan register pressure (PR #132190)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Mar 20 04:47:36 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Sam Tebbs (SamTebbs33)
<details>
<summary>Changes</summary>
Based on fhahn's work at https://github.com/llvm/llvm-project/pull/126437.
This PR moves the register usage checking to after the plans are
created, so that any recipes that optimise register usage (such as
partial reductions) can be properly costed and not have their VF pruned
unnecessarily.
It involves changing some tests, notably removing one from
mve-known-tripcount.ll due to it not being vectorisable thanks to high
register pressure. tail-folding-reduces-vf.ll was modified to reduce its
register pressure but still test what was intended.
---
Patch is 186.33 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/132190.diff
24 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/LoopVectorize.cpp (+293-242)
- (modified) llvm/lib/Transforms/Vectorize/VPRecipeBuilder.h (+2-1)
- (modified) llvm/lib/Transforms/Vectorize/VPlan.h (+10-4)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/i1-reg-usage.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product-neon.ll (+50-10)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-dot-product.ll (+414)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/reg-usage.ll (+6-7)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/ARM/mve-known-trip-count.ll (-191)
- (modified) llvm/test/Transforms/LoopVectorize/ARM/mve-reduction-types.ll (+11-11)
- (modified) llvm/test/Transforms/LoopVectorize/ARM/mve-reductions.ll (+37-37)
- (modified) llvm/test/Transforms/LoopVectorize/ARM/tail-folding-reduces-vf.ll (+4-24)
- (modified) llvm/test/Transforms/LoopVectorize/LoongArch/reg-usage.ll (+4-3)
- (modified) llvm/test/Transforms/LoopVectorize/PowerPC/exit-branch-cost.ll (+48-12)
- (modified) llvm/test/Transforms/LoopVectorize/PowerPC/large-loop-rdx.ll (+77-230)
- (modified) llvm/test/Transforms/LoopVectorize/PowerPC/reg-usage.ll (+9-5)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/reg-usage-bf16.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/reg-usage-f16.ll (+2-2)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/reg-usage.ll (+5-5)
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll (+10-4)
- (modified) llvm/test/Transforms/LoopVectorize/X86/i1-reg-usage.ll (+1-1)
- (modified) llvm/test/Transforms/LoopVectorize/X86/pr47437.ll (+21-99)
- (modified) llvm/test/Transforms/LoopVectorize/X86/reg-usage.ll (+23-9)
- (modified) llvm/test/Transforms/PhaseOrdering/ARM/arm_mean_q7.ll (+18-9)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 89337dc385350..3574aa31195f0 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1018,7 +1018,8 @@ class LoopVectorizationCostModel {
/// If interleave count has been specified by metadata it will be returned.
/// Otherwise, the interleave count is computed and returned. VF and LoopCost
/// are the selected vectorization factor and the cost of the selected VF.
- unsigned selectInterleaveCount(ElementCount VF, InstructionCost LoopCost);
+ unsigned selectInterleaveCount(VPlan &Plan, ElementCount VF,
+ InstructionCost LoopCost);
/// Memory access instruction may be vectorized in more than one way.
/// Form of instruction after vectorization depends on cost.
@@ -1047,11 +1048,6 @@ class LoopVectorizationCostModel {
SmallMapVector<unsigned, unsigned, 4> MaxLocalUsers;
};
- /// \return Returns information about the register usages of the loop for the
- /// given vectorization factors.
- SmallVector<RegisterUsage, 8>
- calculateRegisterUsage(ArrayRef<ElementCount> VFs);
-
/// Collect values we want to ignore in the cost model.
void collectValuesToIgnore();
@@ -4239,27 +4235,12 @@ ElementCount LoopVectorizationCostModel::getMaximizedVFForTarget(
ComputeScalableMaxVF);
MaxVectorElementCountMaxBW = MinVF(MaxVectorElementCountMaxBW, MaxSafeVF);
- // Collect all viable vectorization factors larger than the default MaxVF
- // (i.e. MaxVectorElementCount).
- SmallVector<ElementCount, 8> VFs;
+ // Set the max VF to the largest viable vectorization factor less than or
+ // equal to the max vector element count.
for (ElementCount VS = MaxVectorElementCount * 2;
ElementCount::isKnownLE(VS, MaxVectorElementCountMaxBW); VS *= 2)
- VFs.push_back(VS);
-
- // For each VF calculate its register usage.
- auto RUs = calculateRegisterUsage(VFs);
+ MaxVF = VS;
- // Select the largest VF which doesn't require more registers than existing
- // ones.
- for (int I = RUs.size() - 1; I >= 0; --I) {
- const auto &MLU = RUs[I].MaxLocalUsers;
- if (all_of(MLU, [&](decltype(MLU.front()) &LU) {
- return LU.second <= TTI.getNumberOfRegisters(LU.first);
- })) {
- MaxVF = VFs[I];
- break;
- }
- }
if (ElementCount MinVF =
TTI.getMinimumVF(SmallestType, ComputeScalableMaxVF)) {
if (ElementCount::isKnownLT(MaxVF, MinVF)) {
@@ -4885,8 +4866,245 @@ void LoopVectorizationCostModel::collectElementTypesForWidening() {
}
}
+/// Estimate the register usage for \p Plan and vectorization factors in \p VFs.
+/// Returns the register usage for each VF in \p VFs.
+static SmallVector<LoopVectorizationCostModel::RegisterUsage, 8>
+calculateRegisterUsage(VPlan &Plan, ArrayRef<ElementCount> VFs,
+ const TargetTransformInfo &TTI) {
+ // This function calculates the register usage by measuring the highest number
+ // of values that are alive at a single location. Obviously, this is a very
+ // rough estimation. We scan the loop in a topological order in order and
+ // assign a number to each recipe. We use RPO to ensure that defs are
+ // met before their users. We assume that each recipe that has in-loop
+ // users starts an interval. We record every time that an in-loop value is
+ // used, so we have a list of the first and last occurrences of each
+ // recipe. Next, we transpose this data structure into a multi map that
+ // holds the list of intervals that *end* at a specific location. This multi
+ // map allows us to perform a linear search. We scan the instructions linearly
+ // and record each time that a new interval starts, by placing it in a set.
+ // If we find this value in the multi-map then we remove it from the set.
+ // The max register usage is the maximum size of the set.
+ // We also search for instructions that are defined outside the loop, but are
+ // used inside the loop. We need this number separately from the max-interval
+ // usage number because when we unroll, loop-invariant values do not take
+ // more register.
+ LoopVectorizationCostModel::RegisterUsage RU;
+
+ // Each 'key' in the map opens a new interval. The values
+ // of the map are the index of the 'last seen' usage of the
+ // recipe that is the key.
+ using IntervalMap = SmallDenseMap<VPRecipeBase *, unsigned, 16>;
+
+ // Maps indices to recipes.
+ SmallVector<VPRecipeBase *, 64> Idx2Recipe;
+ // Marks the end of each interval.
+ IntervalMap EndPoint;
+ // Saves the list of recipe indices that are used in the loop.
+ SmallPtrSet<VPRecipeBase *, 8> Ends;
+ // Saves the list of values that are used in the loop but are defined outside
+ // the loop (not including non-recipe values such as arguments and
+ // constants).
+ SmallSetVector<VPValue *, 8> LoopInvariants;
+ LoopInvariants.insert(&Plan.getVectorTripCount());
+
+ ReversePostOrderTraversal<VPBlockDeepTraversalWrapper<VPBlockBase *>> RPOT(
+ Plan.getVectorLoopRegion());
+ for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(RPOT)) {
+ if (!VPBB->getParent())
+ break;
+ for (VPRecipeBase &R : *VPBB) {
+ Idx2Recipe.push_back(&R);
+
+ // Save the end location of each USE.
+ for (VPValue *U : R.operands()) {
+ auto *DefR = U->getDefiningRecipe();
+
+ // Ignore non-recipe values such as arguments, constants, etc.
+ // FIXME: Might need some motivation why these values are ignored. If
+ // for example an argument is used inside the loop it will increase the
+ // register pressure (so shouldn't we add it to LoopInvariants).
+ if (!DefR && (!U->getLiveInIRValue() ||
+ !isa<Instruction>(U->getLiveInIRValue())))
+ continue;
+
+ // If this recipe is outside the loop then record it and continue.
+ if (!DefR) {
+ LoopInvariants.insert(U);
+ continue;
+ }
+
+ // Overwrite previous end points.
+ EndPoint[DefR] = Idx2Recipe.size();
+ Ends.insert(DefR);
+ }
+ }
+ if (VPBB == Plan.getVectorLoopRegion()->getExiting()) {
+ // VPWidenIntOrFpInductionRecipes are used implicitly at the end of the
+ // exiting block, where their increment will get materialized eventually.
+ for (auto &R : Plan.getVectorLoopRegion()->getEntryBasicBlock()->phis()) {
+ if (isa<VPWidenIntOrFpInductionRecipe>(&R)) {
+ EndPoint[&R] = Idx2Recipe.size();
+ Ends.insert(&R);
+ }
+ }
+ }
+ }
+
+ // Saves the list of intervals that end with the index in 'key'.
+ using RecipeList = SmallVector<VPRecipeBase *, 2>;
+ SmallDenseMap<unsigned, RecipeList, 16> TransposeEnds;
+
+ // Transpose the EndPoints to a list of values that end at each index.
+ for (auto &Interval : EndPoint)
+ TransposeEnds[Interval.second].push_back(Interval.first);
+
+ SmallPtrSet<VPRecipeBase *, 8> OpenIntervals;
+ SmallVector<LoopVectorizationCostModel::RegisterUsage, 8> RUs(VFs.size());
+ SmallVector<SmallMapVector<unsigned, unsigned, 4>, 8> MaxUsages(VFs.size());
+
+ LLVM_DEBUG(dbgs() << "LV(REG): Calculating max register usage:\n");
+
+ VPTypeAnalysis TypeInfo(Plan.getCanonicalIV()->getScalarType());
+
+ const auto &TTICapture = TTI;
+ auto GetRegUsage = [&TTICapture](Type *Ty, ElementCount VF) -> unsigned {
+ if (Ty->isTokenTy() || !VectorType::isValidElementType(Ty) ||
+ (VF.isScalable() &&
+ !TTICapture.isElementTypeLegalForScalableVector(Ty)))
+ return 0;
+ return TTICapture.getRegUsageForType(VectorType::get(Ty, VF));
+ };
+
+ for (unsigned int Idx = 0, Sz = Idx2Recipe.size(); Idx < Sz; ++Idx) {
+ VPRecipeBase *R = Idx2Recipe[Idx];
+
+ // Remove all of the recipes that end at this location.
+ RecipeList &List = TransposeEnds[Idx];
+ for (VPRecipeBase *ToRemove : List)
+ OpenIntervals.erase(ToRemove);
+
+ // Ignore recipes that are never used within the loop.
+ if (!Ends.count(R) && !R->mayHaveSideEffects())
+ continue;
+
+ // For each VF find the maximum usage of registers.
+ for (unsigned J = 0, E = VFs.size(); J < E; ++J) {
+ // Count the number of registers used, per register class, given all open
+ // intervals.
+ // Note that elements in this SmallMapVector will be default constructed
+ // as 0. So we can use "RegUsage[ClassID] += n" in the code below even if
+ // there is no previous entry for ClassID.
+ SmallMapVector<unsigned, unsigned, 4> RegUsage;
+
+ if (VFs[J].isScalar()) {
+ for (auto *Inst : OpenIntervals) {
+ for (VPValue *DefV : Inst->definedValues()) {
+ unsigned ClassID = TTI.getRegisterClassForType(
+ false, TypeInfo.inferScalarType(DefV));
+ // FIXME: The target might use more than one register for the type
+ // even in the scalar case.
+ RegUsage[ClassID] += 1;
+ }
+ }
+ } else {
+ for (auto *R : OpenIntervals) {
+ if (isa<VPVectorPointerRecipe, VPVectorEndPointerRecipe>(R))
+ continue;
+ if (isa<VPCanonicalIVPHIRecipe, VPReplicateRecipe, VPDerivedIVRecipe,
+ VPScalarIVStepsRecipe>(R) ||
+ (isa<VPInstruction>(R) &&
+ all_of(cast<VPSingleDefRecipe>(R)->users(), [&](VPUser *U) {
+ return cast<VPRecipeBase>(U)->usesScalars(
+ R->getVPSingleValue());
+ }))) {
+ unsigned ClassID = TTI.getRegisterClassForType(
+ false, TypeInfo.inferScalarType(R->getVPSingleValue()));
+ // FIXME: The target might use more than one register for the type
+ // even in the scalar case.
+ RegUsage[ClassID] += 1;
+ } else {
+ // The output from scaled phis and scaled reductions actually have
+ // fewer lanes than the VF.
+ auto VF = VFs[J];
+ if (auto *ReductionR = dyn_cast<VPReductionPHIRecipe>(R))
+ VF = VF.divideCoefficientBy(ReductionR->getVFScaleFactor());
+ else if (auto *PartialReductionR =
+ dyn_cast<VPPartialReductionRecipe>(R))
+ VF = VF.divideCoefficientBy(PartialReductionR->getScaleFactor());
+ if (VF != VFs[J])
+ LLVM_DEBUG(dbgs() << "LV(REG): Scaled down VF from " << VFs[J]
+ << " to " << VF << " for ";
+ R->dump(););
+
+ for (VPValue *DefV : R->definedValues()) {
+ Type *ScalarTy = TypeInfo.inferScalarType(DefV);
+ unsigned ClassID = TTI.getRegisterClassForType(true, ScalarTy);
+ RegUsage[ClassID] += GetRegUsage(ScalarTy, VF);
+ }
+ }
+ }
+ }
+
+ for (const auto &Pair : RegUsage) {
+ auto &Entry = MaxUsages[J][Pair.first];
+ Entry = std::max(Entry, Pair.second);
+ }
+ }
+
+ LLVM_DEBUG(dbgs() << "LV(REG): At #" << Idx << " Interval # "
+ << OpenIntervals.size() << '\n');
+
+ // Add the current recipe to the list of open intervals.
+ OpenIntervals.insert(R);
+ }
+
+ for (unsigned Idx = 0, End = VFs.size(); Idx < End; ++Idx) {
+ // Note that elements in this SmallMapVector will be default constructed
+ // as 0. So we can use "Invariant[ClassID] += n" in the code below even if
+ // there is no previous entry for ClassID.
+ SmallMapVector<unsigned, unsigned, 4> Invariant;
+
+ for (auto *In : LoopInvariants) {
+ // FIXME: The target might use more than one register for the type
+ // even in the scalar case.
+ bool IsScalar = all_of(In->users(), [&](VPUser *U) {
+ return cast<VPRecipeBase>(U)->usesScalars(In);
+ });
+
+ ElementCount VF = IsScalar ? ElementCount::getFixed(1) : VFs[Idx];
+ unsigned ClassID = TTI.getRegisterClassForType(
+ VF.isVector(), TypeInfo.inferScalarType(In));
+ Invariant[ClassID] += GetRegUsage(TypeInfo.inferScalarType(In), VF);
+ }
+
+ LLVM_DEBUG({
+ dbgs() << "LV(REG): VF = " << VFs[Idx] << '\n';
+ dbgs() << "LV(REG): Found max usage: " << MaxUsages[Idx].size()
+ << " item\n";
+ for (const auto &pair : MaxUsages[Idx]) {
+ dbgs() << "LV(REG): RegisterClass: "
+ << TTI.getRegisterClassName(pair.first) << ", " << pair.second
+ << " registers\n";
+ }
+ dbgs() << "LV(REG): Found invariant usage: " << Invariant.size()
+ << " item\n";
+ for (const auto &pair : Invariant) {
+ dbgs() << "LV(REG): RegisterClass: "
+ << TTI.getRegisterClassName(pair.first) << ", " << pair.second
+ << " registers\n";
+ }
+ });
+
+ RU.LoopInvariantRegs = Invariant;
+ RU.MaxLocalUsers = MaxUsages[Idx];
+ RUs[Idx] = RU;
+ }
+
+ return RUs;
+}
+
unsigned
-LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
+LoopVectorizationCostModel::selectInterleaveCount(VPlan &Plan, ElementCount VF,
InstructionCost LoopCost) {
// -- The interleave heuristics --
// We interleave the loop in order to expose ILP and reduce the loop overhead.
@@ -4936,7 +5154,7 @@ LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
return 1;
}
- RegisterUsage R = calculateRegisterUsage({VF})[0];
+ RegisterUsage R = ::calculateRegisterUsage(Plan, {VF}, TTI)[0];
// We divide by these constants so assume that we have at least one
// instruction that uses at least one register.
for (auto &Pair : R.MaxLocalUsers) {
@@ -5169,213 +5387,6 @@ LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
return 1;
}
-SmallVector<LoopVectorizationCostModel::RegisterUsage, 8>
-LoopVectorizationCostModel::calculateRegisterUsage(ArrayRef<ElementCount> VFs) {
- // This function calculates the register usage by measuring the highest number
- // of values that are alive at a single location. Obviously, this is a very
- // rough estimation. We scan the loop in a topological order in order and
- // assign a number to each instruction. We use RPO to ensure that defs are
- // met before their users. We assume that each instruction that has in-loop
- // users starts an interval. We record every time that an in-loop value is
- // used, so we have a list of the first and last occurrences of each
- // instruction. Next, we transpose this data structure into a multi map that
- // holds the list of intervals that *end* at a specific location. This multi
- // map allows us to perform a linear search. We scan the instructions linearly
- // and record each time that a new interval starts, by placing it in a set.
- // If we find this value in the multi-map then we remove it from the set.
- // The max register usage is the maximum size of the set.
- // We also search for instructions that are defined outside the loop, but are
- // used inside the loop. We need this number separately from the max-interval
- // usage number because when we unroll, loop-invariant values do not take
- // more register.
- LoopBlocksDFS DFS(TheLoop);
- DFS.perform(LI);
-
- RegisterUsage RU;
-
- // Each 'key' in the map opens a new interval. The values
- // of the map are the index of the 'last seen' usage of the
- // instruction that is the key.
- using IntervalMap = SmallDenseMap<Instruction *, unsigned, 16>;
-
- // Maps instruction to its index.
- SmallVector<Instruction *, 64> IdxToInstr;
- // Marks the end of each interval.
- IntervalMap EndPoint;
- // Saves the list of instruction indices that are used in the loop.
- SmallPtrSet<Instruction *, 8> Ends;
- // Saves the list of values that are used in the loop but are defined outside
- // the loop (not including non-instruction values such as arguments and
- // constants).
- SmallSetVector<Instruction *, 8> LoopInvariants;
-
- for (BasicBlock *BB : make_range(DFS.beginRPO(), DFS.endRPO())) {
- for (Instruction &I : BB->instructionsWithoutDebug()) {
- IdxToInstr.push_back(&I);
-
- // Save the end location of each USE.
- for (Value *U : I.operands()) {
- auto *Instr = dyn_cast<Instruction>(U);
-
- // Ignore non-instruction values such as arguments, constants, etc.
- // FIXME: Might need some motivation why these values are ignored. If
- // for example an argument is used inside the loop it will increase the
- // register pressure (so shouldn't we add it to LoopInvariants).
- if (!Instr)
- continue;
-
- // If this instruction is outside the loop then record it and continue.
- if (!TheLoop->contains(Instr)) {
- LoopInvariants.insert(Instr);
- continue;
- }
-
- // Overwrite previous end points.
- EndPoint[Instr] = IdxToInstr.size();
- Ends.insert(Instr);
- }
- }
- }
-
- // Saves the list of intervals that end with the index in 'key'.
- using InstrList = SmallVector<Instruction *, 2>;
- SmallDenseMap<unsigned, InstrList, 16> TransposeEnds;
-
- // Transpose the EndPoints to a list of values that end at each index.
- for (auto &Interval : EndPoint)
- TransposeEnds[Interval.second].push_back(Interval.first);
-
- SmallPtrSet<Instruction *, 8> OpenIntervals;
- SmallVector<RegisterUsage, 8> RUs(VFs.size());
- SmallVector<SmallMapVector<unsigned, unsigned, 4>, 8> MaxUsages(VFs.size());
-
- LLVM_DEBUG(dbgs() << "LV(REG): Calculating max register usage:\n");
-
- const auto &TTICapture = TTI;
- auto GetRegUsage = [&TTICapture](Type *Ty, ElementCount VF) -> unsigned {
- if (Ty->isTokenTy() || !VectorType::isValidElementType(Ty) ||
- (VF.isScalable() &&
- !TTICapture.isElementTypeLegalForScalableVector(Ty)))
- return 0;
- return TTICapture.getRegUsageForType(VectorType::get(Ty, VF));
- };
-
- collectInLoopReductions();
-
- for (unsigned int Idx = 0, Sz = IdxToInstr.size(); Idx < Sz; ++Idx) {
- Instruction *I = IdxToInstr[Idx];
-
- // Remove all of the instructions that end at this location.
- InstrList &List = TransposeEnds[Idx];
- for (Instruction *ToRemove : List)
- OpenIntervals.erase(ToRemove);
-
- // Ignore instructions that are never used within the loop and do not have
- // side-effects.
- if (!Ends.count(I) && !I->mayHaveSideEffects())
- continue;
-
- // Skip ignored values.
- if (ValuesToIgnore.count(I))
- continue;
-
- // For each VF find the maximum usage of registers.
- for (unsigned J = 0, E = VFs.size(); J < E; ++J) {
- // Count the number of registers used, per register class, given all open
- // intervals.
- // Note that elements in this SmallMapVector will be default constructed
- // as 0. So we can use "RegUsage[ClassID] += n" in the code below even if
- // there is no previous entry for ClassID.
- SmallMapVector<unsigned, unsigned, 4> RegUsage;
-
- if (VFs[J].isScalar()) {
- for (auto *Inst : OpenIntervals) {
- unsigned ClassID =
- TTI.getRegisterClassForType(false, Inst->getType());
- // FIXME: The target might use more than one register for the type
- // even in the scalar case.
- RegUsage[ClassID] += 1;
- }
- } else {
- collectUniformsAndScalars(VFs[J]);
- for (auto *Inst : OpenIntervals) {
- // Skip ignored values for VF > 1.
- if (VecValuesToIgnore.count(Inst))
- continue;
- if (isScalarAfterVectorization(Inst, VFs[J])) {
- unsigned ClassID =
- TTI.getRegisterClassForType(false, Inst->getType());
- // FIXME: The target might use more than one register for the type
- // even in the scalar case.
- RegUsage[ClassID] += 1;
- } else {
- unsigned ClassID =
- TTI.getRegisterClassForType(true, Inst->getType());
- RegUsage[ClassID] += GetRegUsage(Inst->getType(), VFs[J]);
- }
- }
- }
-
- for (const auto &Pair : RegUsage) {
- auto &Entry = MaxUsages[J][Pair.first];
- Entry = std::max(Entry, Pair.second);
- }
- }
-
- ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/132190
More information about the llvm-commits
mailing list