[RISCV] Lazily add RVV C intrinsics.

Leverage the method OpenCL uses that adds C intrinsics when the lookup
failed. There is no need to define C intrinsics in the header file any
more. It could help to avoid the large header file to speed up the
compilation of RVV source code. Besides that, only the C intrinsics used
by the users will be added into the declaration table.

This patch is based on https://reviews.llvm.org/D103228 and inspired by
OpenCL implementation.

### Experimental Results

#### TL;DR:

- Binary size of clang increase ~200k, which is +0.07%  for debug build and +0.13% for release build.
- Single file compilation speed up ~33x for debug build and ~8.5x for release build
- Regression time reduce ~10% (`ninja check-all`, enable all targets)

#### Header size change
```
       |      size |     LoC |
------------------------------
Before | 4,434,725 |  69,749 |
After  |     6,140 |     162 |
```

#### Single File Compilation Time
Testcase:
```
#include <riscv_vector.h>

vint32m1_t test_vadd_vv_vfloat32m1_t(vint32m1_t op1, vint32m1_t op2, size_t vl) {
  return vadd(op1, op2, vl);
}
```
##### Debug build:
Before:
```
real    0m19.352s
user    0m19.252s
sys     0m0.092s
```

After:
```
real    0m0.576s
user    0m0.552s
sys     0m0.024s
```

~33x speed up for debug build

##### Release build:
Before:
```
real    0m0.773s
user    0m0.741s
sys     0m0.032s
```

After:
```
real    0m0.092s
user    0m0.080s
sys     0m0.012s
```

~8.5x speed up for release build

#### Regression time
Note: the failed case is `tools/llvm-debuginfod-find/debuginfod.test` which is unrelated to this patch.

##### Debug build
Before:
```
Testing Time: 1358.38s
  Skipped          :    11
  Unsupported      :   446
  Passed           : 75767
  Expectedly Failed:   190
  Failed           :     1
```
After
```
Testing Time: 1220.29s
  Skipped          :    11
  Unsupported      :   446
  Passed           : 75767
  Expectedly Failed:   190
  Failed           :     1
```
##### Release build
Before:
```
Testing Time: 381.98s
  Skipped          :    12
  Unsupported      :  1407
  Passed           : 74765
  Expectedly Failed:   176
  Failed           :     1
```
After:
```
Testing Time: 346.25s
  Skipped          :    12
  Unsupported      :  1407
  Passed           : 74765
  Expectedly Failed:   176
  Failed           :     1
```

#### Binary size of clang

##### Debug build
Before
```
   text    data     bss     dec     hex filename
335261851       12726004         552812 348540667       14c64efb        bin/clang
```
After
```
   text    data     bss     dec     hex filename
335442803       12798708         552940 348794451       14ca2e53        bin/clang
```
+253K, +0.07% code size

##### Release build
Before
```
   text    data     bss     dec     hex filename
144123975       8374648  483140 152981763       91e5103 bin/clang
```
After
```
   text    data     bss     dec     hex filename
144255762       8447296  483268 153186326       9217016 bin/clang
```
+204K, +0.13%

Authored-by: Kito Cheng <kito.cheng@sifive.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>

Reviewed By: khchen, aaron.ballman

Differential Revision: https://reviews.llvm.org/D111617

1 files changed, 52 insertions, 0 deletions

diff --git a/clang/lib/Parse/ParsePragma.cpp b/clang/lib/Parse/ParsePragma.cpp
index 6ca9887..74fa703 100644
--- a/clang/lib/Parse/ParsePragma.cpp
+++ b/clang/lib/Parse/ParsePragma.cpp
@@ -350,6 +350,16 @@ struct PragmaMaxTokensTotalHandler : public PragmaHandler {
                     Token &FirstToken) override;
 };
 
+struct PragmaRISCVHandler : public PragmaHandler {
+  PragmaRISCVHandler(Sema &Actions)
+      : PragmaHandler("riscv"), Actions(Actions) {}
+  void HandlePragma(Preprocessor &PP, PragmaIntroducer Introducer,
+                    Token &FirstToken) override;
+
+private:
+  Sema &Actions;
+};
+
 void markAsReinjectedForRelexing(llvm::MutableArrayRef<clang::Token> Toks) {
   for (auto &T : Toks)
     T.setFlag(clang::Token::IsReinjected);
@@ -493,6 +503,11 @@ void Parser::initializePragmaHandlers() {
 
   MaxTokensTotalPragmaHandler = std::make_unique<PragmaMaxTokensTotalHandler>();
   PP.AddPragmaHandler("clang", MaxTokensTotalPragmaHandler.get());
+
+  if (getTargetInfo().getTriple().isRISCV()) {
+    RISCVPragmaHandler = std::make_unique<PragmaRISCVHandler>(Actions);
+    PP.AddPragmaHandler("clang", RISCVPragmaHandler.get());
+  }
 }
 
 void Parser::resetPragmaHandlers() {
@@ -617,6 +632,11 @@ void Parser::resetPragmaHandlers() {
 
   PP.RemovePragmaHandler("clang", MaxTokensTotalPragmaHandler.get());
   MaxTokensTotalPragmaHandler.reset();
+
+  if (getTargetInfo().getTriple().isRISCV()) {
+    PP.RemovePragmaHandler("clang", RISCVPragmaHandler.get());
+    RISCVPragmaHandler.reset();
+  }
 }
 
 /// Handle the annotation token produced for #pragma unused(...)
@@ -3929,3 +3949,35 @@ void PragmaMaxTokensTotalHandler::HandlePragma(Preprocessor &PP,
 
   PP.overrideMaxTokens(MaxTokens, Loc);
 }
+
+// Handle '#pragma clang riscv intrinsic vector'.
+void PragmaRISCVHandler::HandlePragma(Preprocessor &PP,
+                                      PragmaIntroducer Introducer,
+                                      Token &FirstToken) {
+  Token Tok;
+  PP.Lex(Tok);
+  IdentifierInfo *II = Tok.getIdentifierInfo();
+
+  if (!II || !II->isStr("intrinsic")) {
+    PP.Diag(Tok.getLocation(), diag::warn_pragma_invalid_argument)
+        << PP.getSpelling(Tok) << "riscv" << /*Expected=*/true << "'intrinsic'";
+    return;
+  }
+
+  PP.Lex(Tok);
+  II = Tok.getIdentifierInfo();
+  if (!II || !II->isStr("vector")) {
+    PP.Diag(Tok.getLocation(), diag::warn_pragma_invalid_argument)
+        << PP.getSpelling(Tok) << "riscv" << /*Expected=*/true << "'vector'";
+    return;
+  }
+
+  PP.Lex(Tok);
+  if (Tok.isNot(tok::eod)) {
+    PP.Diag(Tok.getLocation(), diag::warn_pragma_extra_tokens_at_eol)
+        << "clang riscv intrinsic";
+    return;
+  }
+
+  Actions.DeclareRISCVVBuiltins = true;
+}