Unsafe math optimizations implies FTZ (#597)

Fixes #579

Author: alycm

api/footnotes.asciidoc

@@ -148,6 +148,10 @@ Please refer to the OpenCL glossary for the OpenCL definition of thread-safe. \
 This definition may be different from usage of the term in other contexts. \
 ]
 
+:fn-unsafe-denorms-are-zero: pass:n[ \
+As per the definition of `-cl-denorms-are-zero`, the inclusion of this option with `-cl-unsafe-math-optimizations` means that the implementation may flush denormal numbers to zero but is not required to. \
+]
+
 :fn-vendor-id: pass:n[ \
 OpenCL adopters must report a valid vendor ID for their implementation. \
 If there is no valid PCI vendor ID defined for the physical device, implementations must obtain a Khronos vendor ID. \

api/opencl_runtime_layer.asciidoc

@@ -6335,7 +6335,8 @@ rules/specifications for math functions.
     in the unsafe math optimization section of the OpenCL C or OpenCL SPIR-V
     Environment specifications, and (d) may violate edge case behavior in the
     OpenCL C or OpenCL SPIR-V Environment specifications.
-    This option includes the `-cl-no-signed-zeros` and `-cl-mad-enable` options.
+    This option includes the `-cl-no-signed-zeros`, `-cl-mad-enable`, and
+    `-cl-denorms-are-zero` footnote:[{fn-unsafe-denorms-are-zero}] options.
 
 `-cl-finite-math-only` ::
     Allow optimizations for floating-point arithmetic that assume that