@@ -5634,7 +5634,7 @@ endif::cl_khr_fp16[]
56345634The following table describes the following functions:
56355635
56365636 * A subset of functions from <<table-builtin-math,Built-in Scalar and Vector
5637- Argument Math Functions>> that are defined with the half_ prefix .
5637+ Argument Math Functions>> that are defined with the half_ prefix.
56385638 These functions are implemented with a minimum of 10-bits of accuracy,
56395639 i.e. the maximum error value \<= 8192 ulp.
56405640 * A subset of functions from <<table-builtin-math,Built-in Scalar and Vector
@@ -6779,7 +6779,7 @@ ifdef::cl_khr_fp16[]
67796779 int *islessgreater*(half _x_, half _y_) +
67806780 short__n__ *islessgreater*(half__n__ _x_, half__n__ _y_)
67816781endif::cl_khr_fp16[]
6782- | Returns the component-wise compare of (_x_ < _y_) \|\| (_x_ > _y_) .
6782+ | Returns the component-wise compare of (_x_ < _y_) \|\| (_x_ > _y_).
67836783| |
67846784| int *isfinite*(float) +
67856785 int__n__ *isfinite*(float__n__) +
@@ -13595,7 +13595,7 @@ host enqueues the first instance of the nd-range kernel (dp_func_A).
1359513595The kernel dp_func_A will launch a kernel (evaluate_dp_work_A) that will
1359613596determine if new nd-range work needs to be performed.
1359713597If new nd-range work does need to be performed, then evaluate_dp_work_A will
13598- enqueue a new instance of dp_func_A .
13598+ enqueue a new instance of dp_func_A.
1359913599This process is repeated until all the work is completed.
1360013600
1360113601[source,opencl_c]
0 commit comments