[RISCV] Add +optimized-nfN-segment-load-store (#114414)

This is a follow up to #111511, where after benchmarking we learnt that
the Banana Pi F3 has fast segmented loads for not just NF=2, but also
NF=3 and NF=4:
https://github.com/preames/bp3-microarch#vlseg_lmul_x_sew_throughput

This adds tuning features to allow these segment loads and stores to be
costed cheaper and enables it for the spacemit-x60.

It also enables +optimized-nf2-segment-load-store by default in the
generic tuning to maintain the previous behaviour when compiled without
-mcpu or -mtune.

Author: lukel97

llvm/lib/Target/RISCV/RISCVFeatures.td

@@ -1386,6 +1386,13 @@ def TuneOptimizedZeroStrideLoad
                       "true", "Optimized (perform fewer memory operations)"
                       "zero-stride vector load">;
 
+foreach nf = {2-8} in
+  def TuneOptimizedNF#nf#SegmentLoadStore :
+      SubtargetFeature<"optimized-nf"#nf#"-segment-load-store",
+                       "HasOptimizedNF"#nf#"SegmentLoadStore",
+                       "true", "vlseg"#nf#"eN.v and vsseg"#nf#"eN.v are"
+                       "implemented as a wide memory op and shuffle">;
+
 def Experimental
    : SubtargetFeature<"experimental", "HasExperimental",
                       "true", "Experimental intrinsics">;

llvm/lib/Target/RISCV/RISCVProcessors.td

@@ -57,15 +57,19 @@ class RISCVTuneProcessorModel<string n,
                               list<SubtargetFeature> f = []>
     : ProcessorModel<n, m, f,tunef>;
 
+defvar GenericTuneFeatures = [TuneOptimizedNF2SegmentLoadStore];
+
 def GENERIC_RV32 : RISCVProcessorModel<"generic-rv32",
                                        NoSchedModel,
                                        [Feature32Bit,
-                                        FeatureStdExtI]>,
+                                        FeatureStdExtI],
+                                       GenericTuneFeatures>,
                    GenericTuneInfo;
 def GENERIC_RV64 : RISCVProcessorModel<"generic-rv64",
                                        NoSchedModel,
                                        [Feature64Bit,
-                                        FeatureStdExtI]>,
+                                        FeatureStdExtI],
+                                       GenericTuneFeatures>,
                    GenericTuneInfo;
 // Support generic for compatibility with other targets. The triple will be used
 // to change to the appropriate rv32/rv64 version.
@@ -221,7 +225,8 @@ def SIFIVE_U74 : RISCVProcessorModel<"sifive-u74",
 
 defvar SiFiveX280TuneFeatures = !listconcat(SiFive7TuneFeatures,
                                             [TuneDLenFactor2,
-                                             TuneOptimizedZeroStrideLoad]);
+                                             TuneOptimizedZeroStrideLoad,
+                                             TuneOptimizedNF2SegmentLoadStore]);
 def SIFIVE_X280 : RISCVProcessorModel<"sifive-x280", SiFive7Model,
                                       [Feature64Bit,
                                        FeatureStdExtI,
@@ -472,7 +477,10 @@ def SPACEMIT_X60 : RISCVProcessorModel<"spacemit-x60",
                                         FeatureStdExtZvfh,
                                         FeatureStdExtZvkt,
                                         FeatureStdExtZvl256b]),
-                                       [TuneDLenFactor2]>;
+                                       [TuneDLenFactor2,
+                                        TuneOptimizedNF2SegmentLoadStore,
+                                        TuneOptimizedNF3SegmentLoadStore,
+                                        TuneOptimizedNF4SegmentLoadStore]>;
 
 def RP2350_HAZARD3 : RISCVProcessorModel<"rp2350-hazard3",
                                          NoSchedModel,

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -716,6 +716,28 @@ RISCVTTIImpl::getMaskedMemoryOpCost(unsigned Opcode, Type *Src, Align Alignment,
   return getMemoryOpCost(Opcode, Src, Alignment, AddressSpace, CostKind);
 }
 
+static bool hasOptimizedSegmentLoadStore(unsigned NF,
+                                         const RISCVSubtarget *ST) {
+  switch (NF) {
+  case 2:
+    return ST->hasOptimizedNF2SegmentLoadStore();
+  case 3:
+    return ST->hasOptimizedNF3SegmentLoadStore();
+  case 4:
+    return ST->hasOptimizedNF4SegmentLoadStore();
+  case 5:
+    return ST->hasOptimizedNF5SegmentLoadStore();
+  case 6:
+    return ST->hasOptimizedNF6SegmentLoadStore();
+  case 7:
+    return ST->hasOptimizedNF7SegmentLoadStore();
+  case 8:
+    return ST->hasOptimizedNF8SegmentLoadStore();
+  default:
+    llvm_unreachable("Unexpected NF");
+  }
+}
+
 InstructionCost RISCVTTIImpl::getInterleavedMemoryOpCost(
     unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
     Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
@@ -737,9 +759,9 @@ InstructionCost RISCVTTIImpl::getInterleavedMemoryOpCost(
           TLI->isLegalInterleavedAccessType(SubVecTy, Factor, Alignment,
                                             AddressSpace, DL)) {
 
-        // Most available hardware today optimizes NF=2 as as one wide memory op
-        // + Factor * LMUL shuffle ops.
-        if (Factor == 2) {
+        // Some processors optimize segment loads/stores as one wide memory op +
+        // Factor * LMUL shuffle ops.
+        if (hasOptimizedSegmentLoadStore(Factor, ST)) {
           InstructionCost Cost =
               getMemoryOpCost(Opcode, VTy, Alignment, AddressSpace, CostKind);
           MVT SubVecVT = getTLI()->getValueType(DL, SubVecTy).getSimpleVT();