Update graph_optimization.ipynb

louie-tsai · louie-tsai · commit cc191d45278e · 2024-10-10T17:41:54.000-07:00
Signed-off-by: Tsai, Louie &lt;louie.tsai@intel.com&gt;
diff --git a/site/en/guide/graph_optimization.ipynb b/site/en/guide/graph_optimization.ipynb
@@ -101,7 +101,7 @@
         "* *Loop optimizer -* Optimizes the graph control flow by hoisting loop-invariant subgraphs out of loops and by removing redundant stack operations in loops. Also optimizes loops with statically known trip counts and removes statically known dead branches in conditionals.\n",
         "* *Scoped allocator optimizer -* Introduces scoped allocators to reduce data movement and to consolidate some operations.\n",
         "* *Pin to host optimizer -* Swaps small operations onto the CPU. This optimizer is turned OFF by default. \n",
-        "* *Auto mixed precision optimizer -* Converts data types to float16 where applicable to improve performance. Currently applies only to GPUs.\n",
+        "* *Auto mixed precision optimizer -* Converts data types to float16 where applicable to improve performance. Currently applies to GPUs and the latest Intel Xeon CPUs.\n",
         "* *Debug stripper -* Strips nodes related to debugging operations such as `tf.debugging.Assert`, `tf.debugging.check_numerics`, and `tf.print` from the graph. This optimizer is turned OFF by default."
       ]
     },

Original file line number	Diff line number	Diff line change
`@@ -101,7 +101,7 @@`
`101`	`101`	`"* Loop optimizer - Optimizes the graph control flow by hoisting loop-invariant subgraphs out of loops and by removing redundant stack operations in loops. Also optimizes loops with statically known trip counts and removes statically known dead branches in conditionals.\n",`
`102`	`102`	`"* Scoped allocator optimizer - Introduces scoped allocators to reduce data movement and to consolidate some operations.\n",`
`103`	`103`	`"* Pin to host optimizer - Swaps small operations onto the CPU. This optimizer is turned OFF by default. \n",`
`104`		`- "* Auto mixed precision optimizer - Converts data types to float16 where applicable to improve performance. Currently applies only to GPUs.\n",`
	`104`	`+ "* Auto mixed precision optimizer - Converts data types to float16 where applicable to improve performance. Currently applies to GPUs and the latest Intel Xeon CPUs.\n",`
`105`	`105`	"* Debug stripper - Strips nodes related to debugging operations such as `tf.debugging.Assert`, `tf.debugging.check_numerics`, and `tf.print` from the graph. This optimizer is turned OFF by default."
`106`	`106`	`]`
`107`	`107`	`},`