Merge pull request #139 from sx-aurora-dev/merge/vp_merge

Merge/vp merge

Author: kaz7

llvm/docs/LangRef.rst

@@ -17856,6 +17856,67 @@ Example:
       %also.r = select <4 x i1> %cond, <4 x i32> %on_true, <4 x i32> %on_false
 
 
+.. _int_vp_merge:
+
+'``llvm.vp.merge.*``' Intrinsics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+This is an overloaded intrinsic.
+
+::
+
+      declare <16 x i32>  @llvm.vp.merge.v16i32 (<16 x i1> <condition>, <16 x i32> <on_true>, <16 x i32> <on_false>, i32 <pivot>)
+      declare <vscale x 4 x i64>  @llvm.vp.merge.nxv4i64 (<vscale x 4 x i1> <condition>, <vscale x 4 x i64> <on_true>, <vscale x 4 x i64> <on_false>, i32 <pivot>)
+
+Overview:
+"""""""""
+
+The '``llvm.vp.merge``' intrinsic is used to choose one value based on a
+condition vector and an index operand, without IR-level branching.
+
+Arguments:
+""""""""""
+
+The first operand is a vector of ``i1`` and indicates the condition.  The
+second operand is the value that is merged where the condition vector is true.
+The third operand is the value that is selected where the condition vector is
+false or the lane position is greater equal than the pivot. The fourth operand
+is the pivot.
+
+#. The optional ``fast-math flags`` marker indicates that the merge has one or
+   more :ref:`fast-math flags <fastmath>`. These are optimization hints to
+   enable otherwise unsafe floating-point optimizations. Fast-math flags are
+   only valid for merges that return a floating-point scalar or vector type,
+   or an array (nested to any depth) of floating-point scalar or vector types.
+
+Semantics:
+""""""""""
+
+The intrinsic selects lanes from the second and third operand depending on a
+condition vector and pivot value.
+
+For all lanes where the condition vector is true and the lane position is less
+than ``%pivot`` the lane is taken from the second operand.  Otherwise, the lane
+is taken from the third operand.
+
+Example:
+""""""""
+
+.. code-block:: llvm
+
+      %r = call <4 x i32> @llvm.vp.merge.v4i32(<4 x i1> %cond, <4 x i32> %on_true, <4 x i32> %on_false, i32 %pivot)
+
+      ;;; Expansion.
+      ;; Lanes at and above %pivot are taken from %on_false
+      %atfirst = insertelement <4 x i32> undef, i32 %pivot, i32 0
+      %splat = shufflevector <4 x i32> %atfirst, <4 x i32> poison, <4 x i32> zeroinitializer
+      %pivotmask = icmp ult <4 x i32> %splat, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+      %mergemask = and <4 x i1> %cond, <4 x i1> %pivotmask
+      %also.r = select <4 x i1> %mergemask, <4 x i32> %on_true, <4 x i32> %on_false
+
+
 
 .. _int_vp_add:
 

llvm/include/llvm/IR/Intrinsics.td

@@ -1695,6 +1695,12 @@ def int_vp_fma : Intrinsic<[ llvm_anyvector_ty ],
                            [ IntrNoMem, IntrNoSync, IntrWillReturn]>;
 
 
+def int_vp_merge : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                              [ LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                                LLVMMatchType<0>,
+                                LLVMMatchType<0>,
+                                llvm_i32_ty]>;
+
 // Reductions
 let IntrProperties = [IntrSpeculatable, IntrNoMem, IntrNoSync, IntrWillReturn] in {
   def int_vp_reduce_fadd : DefaultAttrsIntrinsic<[LLVMVectorElementType<0>],

llvm/include/llvm/IR/VPIntrinsics.def

@@ -612,6 +612,10 @@ BEGIN_REGISTER_VP_INTRINSIC(vp_vshift, 2, 3)
 BEGIN_REGISTER_VP_SDNODE(VP_VSHIFT, -1, vp_vshift, 2, 3)
 END_REGISTER_CASES(vp_vshift, VP_VSHIFT)
 
+// llvm.vp.merge(mask,on_true,on_false,pivot)
+BEGIN_REGISTER_VP(vp_merge, 0, 3, VP_MERGE, -1)
+END_REGISTER_VP(vp_merge, VP_MERGE)
+
 BEGIN_REGISTER_VP(experimental_vp_splice, 3, 5, EXPERIMENTAL_VP_SPLICE, -1)
 END_REGISTER_VP(experimental_vp_splice, EXPERIMENTAL_VP_SPLICE)
 

llvm/lib/IR/IntrinsicInst.cpp

@@ -593,6 +593,7 @@ static VPIntrinsic::ShortTypeVec getVPIntrinsicTypes(Intrinsic::ID ID,
   case Intrinsic::vp_vshift:
     return VPIntrinsic::ShortTypeVec{VectorTy};
 
+  case Intrinsic::vp_merge:
   case Intrinsic::vp_select:
   case Intrinsic::experimental_vp_splice:
   case Intrinsic::vp_compress:

llvm/unittests/IR/VPIntrinsicTest.cpp

@@ -116,6 +116,8 @@ class VPIntrinsicTest : public testing::Test {
       Str << " declare float @llvm.vp.reduce." << ReductionOpcode
           << ".v8f32(float, <8 x float>, <8 x i1>, i32) ";
 
+    Str << " declare <8 x i32> @llvm.vp.merge.v8i32(<8 x i1>, <8 x i32>, <8 x "
+           "i32>, i32)";
     Str << " declare <8 x i32> @llvm.vp.select.v8i32(<8 x i1>, <8 x i32>, <8 x "
            "i32>, i32)";
     Str << " declare <8 x i32> @llvm.experimental.vp.splice.v8i32(<8 x "