Fix markup for a few extension names.

OpenCL_C.txt

@@ -218,13 +218,13 @@ operations across a work-group.
 
 ifdef::cl_khr_integer_dot_product[]
 | {opencl_c_integer_dot_product_input_4x8bit_packed} +
-  (when the {cl_khr_integer_dot_product} extension macro is defined)
+  (when the `<<cl_khr_integer_dot_product>>` extension macro is defined)
 
 | The OpenCL C compiler supports built-in functions that perform dot
 products on 4x8 bit packed integer vectors
 
 | {opencl_c_integer_dot_product_input_4x8bit} +
-  (when the {cl_khr_integer_dot_product} extension macro is defined)
+  (when the `<<cl_khr_integer_dot_product>>` extension macro is defined)
 | The OpenCL C compiler supports built-in functions that perform dot
 products on 4x8 bit integer vectors
 endif::cl_khr_integer_dot_product[]
@@ -354,7 +354,7 @@ ifdef::cl_khr_fp16[]
 ==== Half-Precision Floating-Point
 
 The `cl_khr_fp16` extension was promoted to OpenCL C 1.2 as an optional
-feature, and to OpenCL 3.0 as the optional {cl_khr_fp16} feature.
+feature, and to OpenCL 3.0 as the optional `<<cl_khr_fp16>>` feature.
 The extension provides 16-bit precision scalar and vector floating-point
 data types and extends many functions to accept these types.
 endif::cl_khr_fp16[]
@@ -365,7 +365,7 @@ ifdef::cl_khr_fp64[]
 ==== Double-Precision Floating-Point
 
 The `cl_khr_fp64` extension was promoted to OpenCL C 1.2 as an optional
-feature, and to OpenCL 3.0 as the optional {cl_khr_fp64} feature.
+feature, and to OpenCL 3.0 as the optional `<<cl_khr_fp64>>` feature.
 The extension provides double-precision scalar and vector floating-point
 data types and extends many functions to accept these types.
 endif::cl_khr_fp64[]