[OpenCL] Add cl_khr_integer_dot_product

Add the builtins defined by Section 42 "Integer dot product" in
the OpenCL Extension Specification.

Differential Revision: https://reviews.llvm.org/D106434

diff --git a/clang/lib/Headers/opencl-c-base.h b/clang/lib/Headers/opencl-c-base.h
index ebc4b7a..1dc52ec 100644 (file)
--- a/clang/lib/Headers/opencl-c-base.h
+++ b/clang/lib/Headers/opencl-c-base.h
@@ -22,6 +22,10 @@
 #define cl_khr_subgroup_shuffle_relative 1
 #define cl_khr_subgroup_clustered_reduce 1
 #define cl_khr_extended_bit_ops 1
+#define cl_khr_integer_dot_product 1
+#define __opencl_c_integer_dot_product_input_4x8bit 1
+#define __opencl_c_integer_dot_product_input_4x8bit_packed 1
+
 #endif // defined(__SPIR__)
 #endif // (defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200)
 

diff --git a/clang/lib/Headers/opencl-c.h b/clang/lib/Headers/opencl-c.h
index 5b3cd05..4be5705 100644 (file)
--- a/clang/lib/Headers/opencl-c.h
+++ b/clang/lib/Headers/opencl-c.h
@@ -16251,6 +16251,30 @@ long16 __ovld __cnfn bit_reverse(long16);
 ulong16 __ovld __cnfn bit_reverse(ulong16);
 #endif // cl_khr_extended_bit_ops
 
+#if defined(__opencl_c_integer_dot_product_input_4x8bit)
+uint __ovld __cnfn dot(uchar4, uchar4);
+int __ovld __cnfn dot(char4, char4);
+int __ovld __cnfn dot(uchar4, char4);
+int __ovld __cnfn dot(char4, uchar4);
+
+uint __ovld __cnfn dot_acc_sat(uchar4, uchar4, uint);
+int __ovld __cnfn dot_acc_sat(char4, char4, int);
+int __ovld __cnfn dot_acc_sat(uchar4, char4, int);
+int __ovld __cnfn dot_acc_sat(char4, uchar4, int);
+#endif // __opencl_c_integer_dot_product_input_4x8bit
+
+#if defined(__opencl_c_integer_dot_product_input_4x8bit_packed)
+uint __ovld __cnfn dot_4x8packed_uu_uint(uint, uint);
+int __ovld __cnfn dot_4x8packed_ss_int(uint, uint);
+int __ovld __cnfn dot_4x8packed_us_int(uint, uint);
+int __ovld __cnfn dot_4x8packed_su_int(uint, uint);
+
+uint __ovld __cnfn dot_acc_sat_4x8packed_uu_uint(uint, uint, uint);
+int __ovld __cnfn dot_acc_sat_4x8packed_ss_int(uint, uint, int);
+int __ovld __cnfn dot_acc_sat_4x8packed_us_int(uint, uint, int);
+int __ovld __cnfn dot_acc_sat_4x8packed_su_int(uint, uint, int);
+#endif // __opencl_c_integer_dot_product_input_4x8bit_packed
+
 #if defined(cl_intel_subgroups)
 // Intel-Specific Sub Group Functions
 float   __ovld __conv intel_sub_group_shuffle( float  x, uint c );

diff --git a/clang/lib/Sema/OpenCLBuiltins.td b/clang/lib/Sema/OpenCLBuiltins.td
index 63def2b..cd704fe 100644 (file)
--- a/clang/lib/Sema/OpenCLBuiltins.td
+++ b/clang/lib/Sema/OpenCLBuiltins.td
@@ -1749,6 +1749,31 @@ let Extension = FuncExtKhrExtendedBitOps in {
   def : Builtin<"bit_reverse", [AIGenTypeN, AIGenTypeN], Attr.Const>;
 }
 
+// Section 42.3 - cl_khr_integer_dot_product
+let Extension = FunctionExtension<"__opencl_c_integer_dot_product_input_4x8bit"> in {
+  def : Builtin<"dot", [UInt, VectorType<UChar, 4>, VectorType<UChar, 4>], Attr.Const>;
+  def : Builtin<"dot", [Int, VectorType<Char, 4>, VectorType<Char, 4>], Attr.Const>;
+  def : Builtin<"dot", [Int, VectorType<UChar, 4>, VectorType<Char, 4>], Attr.Const>;
+  def : Builtin<"dot", [Int, VectorType<Char, 4>, VectorType<UChar, 4>], Attr.Const>;
+
+  def : Builtin<"dot_acc_sat", [UInt, VectorType<UChar, 4>, VectorType<UChar, 4>, UInt], Attr.Const>;
+  def : Builtin<"dot_acc_sat", [Int, VectorType<Char, 4>, VectorType<Char, 4>, Int], Attr.Const>;
+  def : Builtin<"dot_acc_sat", [Int, VectorType<UChar, 4>, VectorType<Char, 4>, Int], Attr.Const>;
+  def : Builtin<"dot_acc_sat", [Int, VectorType<Char, 4>, VectorType<UChar, 4>, Int], Attr.Const>;
+}
+
+let Extension = FunctionExtension<"__opencl_c_integer_dot_product_input_4x8bit_packed"> in {
+  def : Builtin<"dot_4x8packed_uu_uint", [UInt, UInt, UInt], Attr.Const>;
+  def : Builtin<"dot_4x8packed_ss_int", [Int, UInt, UInt], Attr.Const>;
+  def : Builtin<"dot_4x8packed_us_int", [Int, UInt, UInt], Attr.Const>;
+  def : Builtin<"dot_4x8packed_su_int", [Int, UInt, UInt], Attr.Const>;
+
+  def : Builtin<"dot_acc_sat_4x8packed_uu_uint", [UInt, UInt, UInt, UInt], Attr.Const>;
+  def : Builtin<"dot_acc_sat_4x8packed_ss_int", [Int, UInt, UInt, Int], Attr.Const>;
+  def : Builtin<"dot_acc_sat_4x8packed_us_int", [Int, UInt, UInt, Int], Attr.Const>;
+  def : Builtin<"dot_acc_sat_4x8packed_su_int", [Int, UInt, UInt, Int], Attr.Const>;
+}
+
 //--------------------------------------------------------------------
 // Arm extensions.
 let Extension = ArmIntegerDotProductInt8 in {

diff --git a/clang/test/Headers/opencl-c-header.cl b/clang/test/Headers/opencl-c-header.cl
index 18ee9aa..e7d0ae0 100644 (file)
--- a/clang/test/Headers/opencl-c-header.cl
+++ b/clang/test/Headers/opencl-c-header.cl
@@ -126,6 +126,15 @@ global atomic_int z = ATOMIC_VAR_INIT(99);
 #if cl_khr_extended_bit_ops != 1
 #error "Incorrectly defined cl_khr_extended_bit_ops"
 #endif
+#if cl_khr_integer_dot_product != 1
+#error "Incorrectly defined cl_khr_integer_dot_product"
+#endif
+#if __opencl_c_integer_dot_product_input_4x8bit != 1
+#error "Incorrectly defined __opencl_c_integer_dot_product_input_4x8bit"
+#endif
+#if __opencl_c_integer_dot_product_input_4x8bit_packed != 1
+#error "Incorrectly defined __opencl_c_integer_dot_product_input_4x8bit_packed"
+#endif
 
 #else
 
@@ -153,6 +162,15 @@ global atomic_int z = ATOMIC_VAR_INIT(99);
 #ifdef cl_khr_extended_bit_ops
 #error "Incorrect cl_khr_extended_bit_ops define"
 #endif
+#ifdef cl_khr_integer_dot_product
+#error "Incorrect cl_khr_integer_dot_product define"
+#endif
+#ifdef __opencl_c_integer_dot_product_input_4x8bit
+#error "Incorrect __opencl_c_integer_dot_product_input_4x8bit define"
+#endif
+#ifdef __opencl_c_integer_dot_product_input_4x8bit_packed
+#error "Incorrect __opencl_c_integer_dot_product_input_4x8bit_packed define"
+#endif
 
 #endif //(defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200)