Generalize @llvm.ctlz, @llvm.cttz, and @llvm.ctpop to work on vectors of integers...

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134265 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/docs/LangRef.html b/docs/LangRef.html
index 74b2391e294ac261aeba7bd5d4c7b5ca7a27e1fb..bc72144ff71f907f2089d316a956ca315a547f50 100644 (file)
--- a/docs/LangRef.html
+++ b/docs/LangRef.html
@@ -6626,7 +6626,8 @@ LLVM</a>.</p>
 
 <h5>Syntax:</h5>
 <p>This is an overloaded intrinsic. You can use llvm.ctpop on any integer bit
-   width. Not all targets support all bit widths however.</p>
+   width, or on any vector with integer elements. Not all targets support all
+  bit widths or vector types, however.</p>
 
 <pre>
   declare i8 @llvm.ctpop.i8(i8  &lt;src&gt;)
@@ -6634,6 +6635,7 @@ LLVM</a>.</p>
   declare i32 @llvm.ctpop.i32(i32 &lt;src&gt;)
   declare i64 @llvm.ctpop.i64(i64 &lt;src&gt;)
   declare i256 @llvm.ctpop.i256(i256 &lt;src&gt;)
+  declare &lt;2 x i32&gt; @llvm.ctpop.v2i32(&lt;2 x i32&gt; &lt;src&gt;)
 </pre>
 
 <h5>Overview:</h5>
@@ -6642,10 +6644,12 @@ LLVM</a>.</p>
 
 <h5>Arguments:</h5>
 <p>The only argument is the value to be counted.  The argument may be of any
-   integer type.  The return type must match the argument type.</p>
+   integer type, or a vector with integer elements.
+   The return type must match the argument type.</p>
 
 <h5>Semantics:</h5>
-<p>The '<tt>llvm.ctpop</tt>' intrinsic counts the 1's in a variable.</p>
+<p>The '<tt>llvm.ctpop</tt>' intrinsic counts the 1's in a variable, or within each
+   element of a vector.</p>
 
 </div>
 
@@ -6658,7 +6662,8 @@ LLVM</a>.</p>
 
 <h5>Syntax:</h5>
 <p>This is an overloaded intrinsic. You can use <tt>llvm.ctlz</tt> on any
-   integer bit width. Not all targets support all bit widths however.</p>
+   integer bit width, or any vector whose elements are integers. Not all
+   targets support all bit widths or vector types, however.</p>
 
 <pre>
   declare i8 @llvm.ctlz.i8 (i8  &lt;src&gt;)
@@ -6666,6 +6671,7 @@ LLVM</a>.</p>
   declare i32 @llvm.ctlz.i32(i32 &lt;src&gt;)
   declare i64 @llvm.ctlz.i64(i64 &lt;src&gt;)
   declare i256 @llvm.ctlz.i256(i256 &lt;src&gt;)
+  declare &lt;2 x i32&gt; @llvm.ctlz.v2i32(&lt;2 x i32&gt; &lt;src;gt)
 </pre>
 
 <h5>Overview:</h5>
@@ -6674,11 +6680,13 @@ LLVM</a>.</p>
 
 <h5>Arguments:</h5>
 <p>The only argument is the value to be counted.  The argument may be of any
-   integer type. The return type must match the argument type.</p>
+   integer type, or any vector type with integer element type.
+   The return type must match the argument type.</p>
 
 <h5>Semantics:</h5>
 <p>The '<tt>llvm.ctlz</tt>' intrinsic counts the leading (most significant)
-   zeros in a variable.  If the src == 0 then the result is the size in bits of
+   zeros in a variable, or within each element of the vector if the operation
+   is of vector type.  If the src == 0 then the result is the size in bits of
    the type of src. For example, <tt>llvm.ctlz(i32 2) = 30</tt>.</p>
 
 </div>
@@ -6692,7 +6700,8 @@ LLVM</a>.</p>
 
 <h5>Syntax:</h5>
 <p>This is an overloaded intrinsic. You can use <tt>llvm.cttz</tt> on any
-   integer bit width. Not all targets support all bit widths however.</p>
+   integer bit width, or any vector of integer elements. Not all targets
+   support all bit widths or vector types, however.</p>
 
 <pre>
   declare i8 @llvm.cttz.i8 (i8  &lt;src&gt;)
@@ -6700,6 +6709,7 @@ LLVM</a>.</p>
   declare i32 @llvm.cttz.i32(i32 &lt;src&gt;)
   declare i64 @llvm.cttz.i64(i64 &lt;src&gt;)
   declare i256 @llvm.cttz.i256(i256 &lt;src&gt;)
+  declase &lt;2 x i32&gt; @llvm.cttz.v2i32(&lt;2 x i32&gt; &lt;src&gt;)
 </pre>
 
 <h5>Overview:</h5>
@@ -6708,11 +6718,13 @@ LLVM</a>.</p>
 
 <h5>Arguments:</h5>
 <p>The only argument is the value to be counted.  The argument may be of any
-   integer type.  The return type must match the argument type.</p>
+   integer type, or a vectory with integer element type..  The return type
+   must match the argument type.</p>
 
 <h5>Semantics:</h5>
 <p>The '<tt>llvm.cttz</tt>' intrinsic counts the trailing (least significant)
-   zeros in a variable.  If the src == 0 then the result is the size in bits of
+   zeros in a variable, or within each element of a vector.
+   If the src == 0 then the result is the size in bits of
    the type of src.  For example, <tt>llvm.cttz(2) = 1</tt>.</p>
 
 </div>

diff --git a/lib/Transforms/InstCombine/InstCombineCalls.cpp b/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 455cd0a69d5bcf6a8c93ad24a945ce8cd015d497..27e15c3058922b0e00082e627dfc73b9cf8787f7 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -355,7 +355,9 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
   case Intrinsic::cttz: {
     // If all bits below the first known one are known zero,
     // this value is constant.
-    const IntegerType *IT = cast<IntegerType>(II->getArgOperand(0)->getType());
+    const IntegerType *IT = dyn_cast<IntegerType>(II->getArgOperand(0)->getType());
+    // FIXME: Try to simplify vectors of integers.
+    if (!IT) break;
     uint32_t BitWidth = IT->getBitWidth();
     APInt KnownZero(BitWidth, 0);
     APInt KnownOne(BitWidth, 0);
@@ -372,7 +374,9 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
   case Intrinsic::ctlz: {
     // If all bits above the first known one are known zero,
     // this value is constant.
-    const IntegerType *IT = cast<IntegerType>(II->getArgOperand(0)->getType());
+    const IntegerType *IT = dyn_cast<IntegerType>(II->getArgOperand(0)->getType());
+    // FIXME: Try to simplify vectors of integers.
+    if (!IT) break;
     uint32_t BitWidth = IT->getBitWidth();
     APInt KnownZero(BitWidth, 0);
     APInt KnownOne(BitWidth, 0);