add readme

[lizhengxian.123]

Summary

refine vlen to vl

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

static cl::opt<unsigned> VectorizeMemoryCheckThreshold(
     cl::desc("The maximum allowed number of runtime memory checks"));
 
 // Option prefer-predicate-over-epilogue indicates that an epilogue is undesired,
 // that predication is preferred, and this lists all options. I.e., the
 // vectorizer will try to fold the tail-loop (epilogue) into the vector body
 // and predicate the instructions accordingly. If tail-folding fails, there are
 // different fallback strategies depending on these values:
 namespace PreferPredicateTy {
-  enum Option {
-    ScalarEpilogue = 0,
-    PredicateElseScalarEpilogue,
-    VlenElseScalarEpilogue,
-    PredicateOrDontVectorize
-  };
+  VlElseScalarEpilogue,
 } // namespace PreferPredicateTy
 
 static cl::opt<PreferPredicateTy::Option> PreferPredicateOverEpilogue(
     "prefer-predicate-over-epilogue",
-    cl::init(PreferPredicateTy::ScalarEpilogue),
-    cl::Hidden,
+    cl::init(PreferPredicateTy::ScalarEpilogue), cl::Hidden,
     cl::desc("Tail-folding and predication preferences over creating a scalar "
              "epilogue loop."),
-    cl::values(clEnumValN(PreferPredicateTy::ScalarEpilogue,
-                         "scalar-epilogue",
-                         "Don't tail-predicate loops, create scalar epilogue"),
-              clEnumValN(PreferPredicateTy::PredicateElseScalarEpilogue,
-                         "predicate-else-scalar-epilogue",
-                         "prefer tail-folding, create scalar epilogue if tail "
-                         "folding fails."),
-              clEnumValN(PreferPredicateTy::VlenElseScalarEpilogue,
-                         "vlen-else-scalar-epilogue",
-                         "prefer tail-folding, we use dynamic vlen to support it. Only works for rvv, create scalar epilogue if tail "
-                         "folding fails."),
-              clEnumValN(PreferPredicateTy::PredicateOrDontVectorize,
-                         "predicate-dont-vectorize",
-                         "prefers tail-folding, don't attempt vectorization if "
-                         "tail-folding fails.")));
+    cl::values(
+        clEnumValN(PreferPredicateTy::ScalarEpilogue, "scalar-epilogue",
+        clEnumValN(PreferPredicateTy::VlElseScalarEpilogue,
+                   "prefer tail-folding, we use dynamic vlen to support it. "
+                   "Only works for rvv, create scalar epilogue if tail "
 
 static cl::opt<bool> MaximizeBandwidth(
     "vectorizer-maximize-bandwidth", cl::init(false), cl::Hidden,
     cl::desc("Maximize bandwidth when selecting vectorization factor which "
              "will be determined by the smallest type in loop."));
 
 static cl::opt<bool> EnableInterleavedMemAccesses(
     "enable-interleaved-mem-accesses", cl::init(false), cl::Hidden,
enum ScalarEpilogueLowering {
   // trip count are considered for vectorization under OptForSize, thereby
   // making sure the cost of their loop body is dominant, free of runtime
   // guards and scalar iteration overheads.
   CM_ScalarEpilogueNotAllowedLowTripLoop,
 
   // Loop hint predicate indicating an epilogue is undesired.
   CM_ScalarEpilogueNotNeededUsePredicate,
 
-  CM_ScalarEpilogueNotNeededUseVlen,
+  CM_ScalarEpilogueNotNeededUseVl,
 
   // Directive indicating we must either tail fold or not vectorize
   CM_ScalarEpilogueNotAllowedUsePredicate
 };
 
 /// ElementCountComparator creates a total ordering for ElementCount
 /// for the purposes of using it in a set structure.
 struct ElementCountComparator {
if (TC == 1) {
     return FixedScalableVFPair::getNone();
   }
 
   switch (ScalarEpilogueStatus) {
   case CM_ScalarEpilogueAllowed:
     return computeFeasibleMaxVF(TC, UserVF, false);
   case CM_ScalarEpilogueNotAllowedUsePredicate:
     LLVM_FALLTHROUGH;
-  case CM_ScalarEpilogueNotNeededUseVlen:
-     LLVM_DEBUG(errs() << "LV: vector Vlen hint/switch found.\n"
+  case CM_ScalarEpilogueNotNeededUseVl:
                       << "LV: Not allowing scalar epilogue, creating vlenset "
                       << "vector loop.\n";);
-     break;
   case CM_ScalarEpilogueNotNeededUsePredicate:
     LLVM_DEBUG(
         dbgs() << "LV: vector predicate hint/switch found.\n"
                << "LV: Not allowing scalar epilogue, creating predicated "
                << "vector loop.\n");
     break;
   case CM_ScalarEpilogueNotAllowedLowTripLoop:
     // fallthrough as a special case of OptForSize
LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
 
   // The only loops we can vectorize without a scalar epilogue, are loops with
   // a bottom-test and a single exiting block. We'd have to handle the fact
   // that not every instruction executes on the last iteration.  This will
   // require a lane mask which varies through the vector loop body.  (TODO)
   if (TheLoop->getExitingBlock() != TheLoop->getLoopLatch()) {
     // If there was a tail-folding hint/switch, but we can't fold the tail by
     // masking, fallback to a vectorization with a scalar epilogue.
-    if (ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUsePredicate|| ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUseVlen) {
+    if (ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUsePredicate ||
+        ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUseVl) {
       LLVM_DEBUG(dbgs() << "LV: Cannot fold tail by masking or vlen: vectorize with a "
                            "scalar epilogue instead.\n");
       ScalarEpilogueStatus = CM_ScalarEpilogueAllowed;
       return computeFeasibleMaxVF(TC, UserVF, false);
     }
     return FixedScalableVFPair::getNone();
   }
 
LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
   }
 
   // If we don't know the precise trip count, or if the trip count that we
   // found modulo the vectorization factor is not zero, try to fold the tail
   // by masking.
   // FIXME: look for a smaller MaxVF that does divide TC rather than masking.
   if (Legal->prepareToFoldTailByMasking()) {
     FoldTailByMasking = true;
-    if (ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUseVlen)
+    if (ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUseVl)
       FoldTailByImplictMasking = true;
     return MaxFactors;
   }
   // If there was a tail-folding hint/switch, but we can't fold the tail by
   // masking, fallback to a vectorization with a scalar epilogue.
-  if (ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUsePredicate|| 
-      ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUseVlen) {
+  if (ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUsePredicate ||
+      ScalarEpilogueStatus == CM_ScalarEpilogueNotNeededUseVl) {
     LLVM_DEBUG(dbgs() << "LV: Cannot fold tail by masking or vlen: vectorize with a "
                          "scalar epilogue instead.\n");
     ScalarEpilogueStatus = CM_ScalarEpilogueAllowed;
     return MaxFactors;
   }
 
   if (ScalarEpilogueStatus == CM_ScalarEpilogueNotAllowedUsePredicate) {
     LLVM_DEBUG(dbgs() << "LV: Can't fold tail by masking: don't vectorize\n");
if (F->hasOptSize() || (llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI,
                           Hints.getForce() != LoopVectorizeHints::FK_Enabled))
     return CM_ScalarEpilogueNotAllowedOptSize;
 
   // 2) If set, obey the directives
   if (PreferPredicateOverEpilogue.getNumOccurrences()) {
     switch (PreferPredicateOverEpilogue) {
     case PreferPredicateTy::ScalarEpilogue:
       return CM_ScalarEpilogueAllowed;
-    case PreferPredicateTy::VlenElseScalarEpilogue:
-      return  CM_ScalarEpilogueNotNeededUseVlen;
+    case PreferPredicateTy::VlElseScalarEpilogue:
+      return CM_ScalarEpilogueNotNeededUseVl;
     case PreferPredicateTy::PredicateElseScalarEpilogue:
       return CM_ScalarEpilogueNotNeededUsePredicate;
     case PreferPredicateTy::PredicateOrDontVectorize:
       return CM_ScalarEpilogueNotAllowedUsePredicate;
     };
   }
 
   // 3) If set, obey the hints

vectorizationREADME.md

 # 向量化tail folding功能实现
 ## 注意事项
 添加新选项： 
-```--prefer-predicate-over-epilogue=vlen-else-scalar-epilogue ``` 
+```--prefer-predicate-over-epilogue=vlen-else-scalar-epilogue ``` ,可以在riscv 后端使用vsetvl指令进行tail folding
+在test/Transform/LoopVectorize/RISCV添加测试prefer_tail_folding_with_vsetvl.ll 测试，是由arm下的文件修改而来，满足了关于各种类型，各种类型混合，指定向量宽度后下tail_folding的正确性
+【WIP】：vector scatter gather 基于目前基础设施无法实现tail folding ,直接用assert表示
 ## 环境
 类似于如下构建
 ```
   #!/bin/sh
 GNU_TOOLCHAIN_PREFIX=$(pwd)/riscv-gnu-toolchain-install
 QEMU_PREFIX=$(pwd)/qemu-install
 export LLVM_INSTALL=$(pwd)/llvm-dev/llvm_community/bytedance-riscv/llvm-project/build
 export PATH=$GNU_TOOLCHAIN_PREFIX/bin:$QEMU_PREFIX/bin:$LLVM_INSTALL/bin:$PATH

 ## 文档记录
 [rvv消除记录](https://bytedance.feishu.cn/docx/doxcnBkVyNOE7E7Y8pjwPgzfCUM)
 
 ## 实现原理
 简而言之，照着```--prefer-predicate-over-epilogue ``` 指令描，搞定vsetvl, vstore, vload 的写法。
 
 向量化的过程是: ir -> vplan -> ir
 我们目前只关注vplan ->ir 这部分，相当于codegen
 No newline at end of file