commit ab99b59e8ca28f5366fb95b497e64ae44d67a9ca
author Jeroen Ketema <j.ketema@imperial.ac.uk> Wed Sep 30 10:56:37 2015 +0000
committer Jeroen Ketema <j.ketema@imperial.ac.uk> Wed Sep 30 10:56:37 2015 +0000
tree a9b8c1d1af1f1c409aa1e51dcfd9ea96fdf314f1
parent 42e651fa43747743a6161b1c53e59c743d52a71c

[ARM][NEON] Use address space in vld([1234]|[234]lane) and vst([1234]|[234]lane) instructions

This commit changes the interface of the vld[1234], vld[234]lane, and vst[1234],
vst[234]lane ARM neon intrinsics and associates an address space with the
pointer that these intrinsics take. This changes, e.g.,

<2 x i32> @llvm.arm.neon.vld1.v2i32(i8*, i32)

to

<2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8(i8*, i32)

This change ensures that address spaces are fully taken into account in the ARM
target during lowering of interleaved loads and stores.

Differential Revision: http://reviews.llvm.org/D12985

llvm-svn: 248887

llvm/lib/IR/AutoUpgrade.cpp

diff --git a/llvm/lib/IR/AutoUpgrade.cpp b/llvm/lib/IR/AutoUpgrade.cpp
index 22ff7d3..6c9fdd6 100644
--- a/llvm/lib/IR/AutoUpgrade.cpp
+++ b/llvm/lib/IR/AutoUpgrade.cpp
@@ -27,6 +27,7 @@
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/Regex.h"
 #include <cstring>
 using namespace llvm;
 
@@ -92,8 +93,41 @@
                                         F->arg_begin()->getType());
       return true;
     }
+    Regex vldRegex("^arm\\.neon\\.vld([1234]|[234]lane)\\.v[a-z0-9]*$");
+    if (vldRegex.match(Name)) {
+      auto fArgs = F->getFunctionType()->params();
+      SmallVector<Type *, 4> Tys(fArgs.begin(), fArgs.end());
+      // Can't use Intrinsic::getDeclaration here as the return types might
+      // then only be structurally equal.
+      FunctionType* fType = FunctionType::get(F->getReturnType(), Tys, false);
+      NewFn = Function::Create(fType, F->getLinkage(),
+                               "llvm." + Name + ".p0i8", F->getParent());
+      return true;
+    }
+    Regex vstRegex("^arm\\.neon\\.vst([1234]|[234]lane)\\.v[a-z0-9]*$");
+    if (vstRegex.match(Name)) {
+      static Intrinsic::ID StoreInts[] = {Intrinsic::arm_neon_vst1,
+                                          Intrinsic::arm_neon_vst2,
+                                          Intrinsic::arm_neon_vst3,
+                                          Intrinsic::arm_neon_vst4};
+
+      static Intrinsic::ID StoreLaneInts[] = {Intrinsic::arm_neon_vst2lane,
+                                              Intrinsic::arm_neon_vst3lane,
+                                              Intrinsic::arm_neon_vst4lane};
+
+      auto fArgs = F->getFunctionType()->params();
+      Type *Tys[] = {fArgs[0], fArgs[1]};
+      if (Name.find("lane") == StringRef::npos)
+        NewFn = Intrinsic::getDeclaration(F->getParent(),
+                                          StoreInts[fArgs.size() - 3], Tys);
+      else
+        NewFn = Intrinsic::getDeclaration(F->getParent(),
+                                          StoreLaneInts[fArgs.size() - 5], Tys);
+      return true;
+    }
     break;
   }
+
   case 'c': {
     if (Name.startswith("ctlz.") && F->arg_size() == 1) {
       F->setName(Name + ".old");
@@ -651,6 +685,27 @@
   default:
     llvm_unreachable("Unknown function for CallInst upgrade.");
 
+  case Intrinsic::arm_neon_vld1:
+  case Intrinsic::arm_neon_vld2:
+  case Intrinsic::arm_neon_vld3:
+  case Intrinsic::arm_neon_vld4:
+  case Intrinsic::arm_neon_vld2lane:
+  case Intrinsic::arm_neon_vld3lane:
+  case Intrinsic::arm_neon_vld4lane:
+  case Intrinsic::arm_neon_vst1:
+  case Intrinsic::arm_neon_vst2:
+  case Intrinsic::arm_neon_vst3:
+  case Intrinsic::arm_neon_vst4:
+  case Intrinsic::arm_neon_vst2lane:
+  case Intrinsic::arm_neon_vst3lane:
+  case Intrinsic::arm_neon_vst4lane: {
+    SmallVector<Value *, 4> Args(CI->arg_operands().begin(),
+                                 CI->arg_operands().end());
+    CI->replaceAllUsesWith(Builder.CreateCall(NewFn, Args));
+    CI->eraseFromParent();
+    return;
+  }
+
   case Intrinsic::ctlz:
   case Intrinsic::cttz:
     assert(CI->getNumArgOperands() == 1 &&