提交 e26aac4e authored 作者: Arnaud Bergeron's avatar Arnaud Bergeron

Fix some typos/phrasings.

上级 6ab5e670
...@@ -223,9 +223,9 @@ Here is the same kernel, but now ready to handle float16:: ...@@ -223,9 +223,9 @@ Here is the same kernel, but now ready to handle float16::
""" """
KERNEL void k(const ga_size n, %(type_x)s *x, %(type_y)s *y) { KERNEL void k(const ga_size n, %(type_x)s *x, %(type_y)s *y) {
ga_size i = GID_0 * LDIM_0 + LID_0; ga_size i = GID_0 * LDIM_0 + LID_0;
%(work_x) z = %(load_w)(x[i]); %(work_x) z = %(load_x)(x[i]);
z += 1; z += 1;
y[i] = %(write_w)(z); y[i] = %(write_y)(z);
} }
""" % dict(dtype_x=dtype_x, dtype_y=dtype_y, work_x=work_x, load_x=load_x, """ % dict(dtype_x=dtype_x, dtype_y=dtype_y, work_x=work_x, load_x=load_x,
write_y=write_y) write_y=write_y)
...@@ -239,7 +239,8 @@ class property like this:: ...@@ -239,7 +239,8 @@ class property like this::
_f16_ok = True _f16_ok = True
If this attribute is not present or is False, the linker will print a If this attribute is not present or is False, the linker will print a
message saying that it's refusing to use C code for float16. message saying that it's refusing to use C code for float16 for the
op.
A Complete Example A Complete Example
================== ==================
......
...@@ -18,7 +18,7 @@ def load_w(dtype): ...@@ -18,7 +18,7 @@ def load_w(dtype):
This should be used like this:: This should be used like this::
code = '%(load_f)s(ival)' % (load_w(input_type),) code = '%s(ival)' % (load_w(input_type),)
""" """
if dtype == 'float16': if dtype == 'float16':
...@@ -33,7 +33,7 @@ def write_w(dtype): ...@@ -33,7 +33,7 @@ def write_w(dtype):
This should be used like this:: This should be used like this::
code = 'res = %(write_f)s(oval)' % (write_w(output_type),) code = 'res = %s(oval)' % (write_w(output_type),)
""" """
if dtype == 'float16': if dtype == 'float16':
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论