On the powerpc, switch statements can be expensive, and we would like to be
able to tune the threshold of when the compiler generates if statements
vs. using a table jump operation (and different processors within the powerpc
have different limits). This patch adds a powerpc tuning option to control
this.
I've done bootstraps and make checks with no regressions. Is this ok to apply
to the trunk? At this time, I am not changing the default value (4). With the
option, I've seen a few spec 2006 benchmarks run faster, and a few run slower.
[gcc]
2011-06-29 Michael Meissner <meiss...@linux.vnet.ibm.com>
* config/rs6000/rs6000.opt (-mcase-values-threshold): New switch.
* config/rs6000/rs6000.c (TARGET_CASE_VALUES_THRESHOLD): New
target hook for override choice of when to do jump table vs. if
statements based on -mcase-values-threshold=<n>.
* doc/invoke.texi (RS/6000 and PowerPC Options): Document
-mcase-values-threshold.
[gcc/testsuite]
2011-06-29 Michael Meissner <meiss...@linux.vnet.ibm.com>
* gcc.target/powerpc/ppc-switch-1.c: New test for
-mcase-values-threshold.
* gcc.target/powerpc/ppc-switch-2.c: Ditto.
--
Michael Meissner, IBM
5 Technology Place Drive, M/S 2757, Westford, MA 01886-3141, USA
meiss...@linux.vnet.ibm.com fax +1 (978) 399-6899
Index: gcc/config/rs6000/rs6000.opt
===================================================================
--- gcc/config/rs6000/rs6000.opt (revision 175662)
+++ gcc/config/rs6000/rs6000.opt (working copy)
@@ -521,4 +521,7 @@ mxilinx-fpu
Target Var(rs6000_xilinx_fpu) Save
Specify Xilinx FPU.
-
+mcase-values-threshold=
+Target Report Var(rs6000_case_values_threshold_num) Init(4) RejectNegative
Joined UInteger Save
+Specify the smallest number of different values for which it is best to use a
+jump-table instead of a tree of conditional branches (default, 4).
Index: gcc/config/rs6000/rs6000.c
===================================================================
--- gcc/config/rs6000/rs6000.c (revision 175662)
+++ gcc/config/rs6000/rs6000.c (working copy)
@@ -1210,6 +1210,7 @@ static void rs6000_function_specific_pri
struct cl_target_option *);
static bool rs6000_can_inline_p (tree, tree);
static void rs6000_set_current_function (tree);
+static unsigned int rs6000_case_values_threshold (void);
/* Default register names. */
@@ -1617,6 +1618,9 @@ static const struct attribute_spec rs600
#undef TARGET_LEGITIMATE_CONSTANT_P
#define TARGET_LEGITIMATE_CONSTANT_P rs6000_legitimate_constant_p
+#undef TARGET_CASE_VALUES_THRESHOLD
+#define TARGET_CASE_VALUES_THRESHOLD rs6000_case_values_threshold
+
struct gcc_target targetm = TARGET_INITIALIZER;
@@ -26834,6 +26838,18 @@ rs6000_libcall_value (enum machine_mode
return gen_rtx_REG (mode, regno);
}
+/* If the machine does not have a case insn that compares the bounds,
+ this means extra overhead for dispatch tables, which raises the
+ threshold for using them. */
+
+static unsigned int
+rs6000_case_values_threshold (void)
+{
+ if (rs6000_case_values_threshold_num)
+ return rs6000_case_values_threshold_num;
+
+ return default_case_values_threshold ();
+}
/* Given FROM and TO register numbers, say whether this elimination is allowed.
Frame pointer elimination is automatically handled.
Index: gcc/doc/invoke.texi
===================================================================
--- gcc/doc/invoke.texi (revision 175662)
+++ gcc/doc/invoke.texi (working copy)
@@ -807,7 +807,7 @@ See RS/6000 and PowerPC Options.
-msdata=@var{opt} -mvxworks -G @var{num} -pthread @gol
-mrecip -mrecip=@var{opt} -mno-recip -mrecip-precision @gol
-mno-recip-precision @gol
--mveclibabi=@var{type} -mfriz -mno-friz}
+-mveclibabi=@var{type} -mfriz -mno-friz -mcase-values-threshold=@var{n}}
@emph{RX Options}
@gccoptlist{-m64bit-doubles -m32bit-doubles -fpu -nofpu@gol
@@ -16320,6 +16320,11 @@ Generate (do not generate) the @code{fri
rounding a floating point value to 64-bit integer and back to floating
point. The @code{friz} instruction does not return the same value if
the floating point number is too large to fit in an integer.
+
+@item -mcase-values-threshold=@var{n}
+Specify the smallest number of different values for which it is best to
+use a jump-table instead of a tree of conditional branches. The
+default for @option{-mcase-values-threshold} is 4.
@end table
@node RX Options
Index: gcc/testsuite/gcc.target/powerpc/ppc-switch-1.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/ppc-switch-1.c (revision 0)
+++ gcc/testsuite/gcc.target/powerpc/ppc-switch-1.c (revision 0)
@@ -0,0 +1,26 @@
+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-skip-if "" { powerpc*-*-darwin* } { "*" } { "" } } */
+/* { dg-options "-O2 -mcase-values-threshold=2" } */
+/* { dg-final { scan-assembler "mtctr" } } */
+/* { dg-final { scan-assembler "bctr" } } */
+
+/* Force using a dispatch table even though by default we would generate
+ ifs. */
+
+extern long call (long);
+
+long
+test_switch (long a, long b)
+{
+ long c;
+
+ switch (a)
+ {
+ case 0: c = -b; break;
+ case 1: c = ~b; break;
+ case 2: c = b+1; break;
+ default: c = b & 9; break;
+ }
+
+ return call (c) + 1;
+}
Index: gcc/testsuite/gcc.target/powerpc/ppc-switch-2.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/ppc-switch-2.c (revision 0)
+++ gcc/testsuite/gcc.target/powerpc/ppc-switch-2.c (revision 0)
@@ -0,0 +1,32 @@
+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-skip-if "" { powerpc*-*-darwin* } { "*" } { "" } } */
+/* { dg-options "-O2 -mcase-values-threshold=20" } */
+/* { dg-final { scan-assembler-not "mtctr" } } */
+/* { dg-final { scan-assembler-not "bctr" } } */
+
+/* Force using if tests, instead of a dispatch table. */
+
+extern long call (long);
+
+long
+test_switch (long a, long b)
+{
+ long c;
+
+ switch (a)
+ {
+ case 0: c = -b; break;
+ case 1: c = ~b; break;
+ case 2: c = b+1; break;
+ case 3: c = b-2; break;
+ case 4: c = b*3; break;
+ case 5: c = b/4; break;
+ case 6: c = b<<5; break;
+ case 7: c = b>>6; break;
+ case 8: c = b|7; break;
+ case 9: c = b^8; break;
+ default: c = b&9; break;
+ }
+
+ return call (c) + 1;
+}
