aarch64: Add --params to control the number of recip steps [PR94154]

-mlow-precision-div hard-coded the number of iterations to 2 for double
and 1 for float.  This patch adds a --param to control the number.

2020-03-13  Bu Le  <bule1@huawei.com>

gcc/
	PR target/94154
	* config/aarch64/aarch64.opt (-param=aarch64-float-recp-precision=)
	(-param=aarch64-double-recp-precision=): New options.
	* doc/invoke.texi: Document them.
	* config/aarch64/aarch64.c (aarch64_emit_approx_div): Use them
	instead of hard-coding the choice of 1 for float and 2 for double.

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 61982897e1194c3120cfd3a6f6cf247b56d3e6ec..ac8940a25f7fe5e259f5ffff98c0f71c6fb2c42d 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,12 @@
+2020-03-13  Bu Le  <bule1@huawei.com>
+
+       PR target/94154
+       * config/aarch64/aarch64.opt (-param=aarch64-float-recp-precision=)
+       (-param=aarch64-double-recp-precision=): New options.
+       * doc/invoke.texi: Document them.
+       * config/aarch64/aarch64.c (aarch64_emit_approx_div): Use them
+       instead of hard-coding the choice of 1 for float and 2 for double.
+
 2019-03-13  Eric Botcazou  <ebotcazou@adacore.com>
 
        PR rtl-optimization/94119

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index c320d5ba51d9bd9130e7f4a36cc27c9ba8d88c9c..2c81f86dd2ae9d377a4bd3372ee83e133401f256 100644 (file)
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -12911,10 +12911,12 @@ aarch64_emit_approx_div (rtx quo, rtx num, rtx den)
   /* Iterate over the series twice for SF and thrice for DF.  */
   int iterations = (GET_MODE_INNER (mode) == DFmode) ? 3 : 2;
 
-  /* Optionally iterate over the series once less for faster performance,
-     while sacrificing the accuracy.  */
+  /* Optionally iterate over the series less for faster performance,
+     while sacrificing the accuracy.  The default is 2 for DF and 1 for SF.  */
   if (flag_mlow_precision_div)
-    iterations--;
+    iterations = (GET_MODE_INNER (mode) == DFmode
+                 ? aarch64_double_recp_precision
+                 : aarch64_float_recp_precision);
 
   /* Iterate over the series to calculate the approximate reciprocal.  */
   rtx xtmp = gen_reg_rtx (mode);

diff --git a/gcc/config/aarch64/aarch64.opt b/gcc/config/aarch64/aarch64.opt
index 77df0b77f8c7acb1c635eb234898a71599680e8b..37181b5baca049eadb4a4bf2e66e68866d08c967 100644 (file)
--- a/gcc/config/aarch64/aarch64.opt
+++ b/gcc/config/aarch64/aarch64.opt
@@ -262,3 +262,12 @@ Generate local calls to out-of-line atomic operations.
 -param=aarch64-sve-compare-costs=
 Target Joined UInteger Var(aarch64_sve_compare_costs) Init(1) IntegerRange(0, 1) Param
 When vectorizing for SVE, consider using unpacked vectors for smaller elements and use the cost model to pick the cheapest approach.  Also use the cost model to choose between SVE and Advanced SIMD vectorization.
+
+-param=aarch64-float-recp-precision=
+Target Joined UInteger Var(aarch64_float_recp_precision) Init(1) IntegerRange(1, 5) Param
+The number of Newton iterations for calculating the reciprocal for float type.  The precision of division is proportional to this param when division approximation is enabled.  The default value is 1.
+
+-param=aarch64-double-recp-precision=
+Target Joined UInteger Var(aarch64_double_recp_precision) Init(2) IntegerRange(1, 5) Param
+The number of Newton iterations for calculating the reciprocal for double type.  The precision of division is proportional to this param when division approximation is enabled.  The default value is 2.
+

diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index af28015234c7e8cd4a2a081f3abbc801eac951cb..96a95162696b922ea7bccb2997b1703d1f5576bf 100644 (file)
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -13179,6 +13179,17 @@ Also use the cost model to choose between SVE and Advanced SIMD vectorization.
 Using unpacked vectors includes storing smaller elements in larger
 containers and accessing elements with extending loads and truncating
 stores.
+
+@item aarch64-float-recp-precision
+The number of Newton iterations for calculating the reciprocal for float type.
+The precision of division is proportional to this param when division
+approximation is enabled.  The default value is 1.
+
+@item aarch64-double-recp-precision
+The number of Newton iterations for calculating the reciprocal for double type.
+The precision of division is propotional to this param when division
+approximation is enabled.  The default value is 2.
+
 @end table
 
 @end table