This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: Remove redundant AND from count reduction loop
- From: Richard Sandiford <richard dot sandiford at arm dot com>
- To: Richard Biener <richard dot guenther at gmail dot com>
- Cc: GCC Patches <gcc-patches at gcc dot gnu dot org>
- Date: Thu, 25 Jun 2015 12:51:54 +0100
- Subject: Re: Remove redundant AND from count reduction loop
- Authentication-results: sourceware.org; auth=none
- References: <87pp4m8mkp dot fsf at e105548-lin dot cambridge dot arm dot com> <alpine dot DEB dot 2 dot 20 dot 1506232307180 dot 1715 at laptop-mg dot saclay dot inria dot fr> <CAFiYyc0F3YqAjr2+EMf8STUBrVN+bE3aYpC+1nnstSaf2oiaDg at mail dot gmail dot com> <87egl1sa2p dot fsf at e105548-lin dot cambridge dot arm dot com> <CAFiYyc0_JiQSZ=M1NqZAaDgh6kYy_EXtpZp9cd2NJOtTG46ang at mail dot gmail dot com> <87a8vps6p1 dot fsf at e105548-lin dot cambridge dot arm dot com> <CAFiYyc1M4-j8QOWSkowHp8fh5D9ScYACEDPQ0KHH52tEBrP54g at mail dot gmail dot com> <871th1s322 dot fsf at e105548-lin dot cambridge dot arm dot com> <CAFiYyc1Q_NJftYjH49v+konjyiOZw_hzJ6un31R_mizdhk60=w at mail dot gmail dot com> <87twtxqlbq dot fsf at e105548-lin dot cambridge dot arm dot com> <CAFiYyc3qGd_L-dSGN7vefXV+901xhWj0YfYk0pA_w5C9VxwQ4A at mail dot gmail dot com> <87pp4kqk4l dot fsf at e105548-lin dot cambridge dot arm dot com> <CAFiYyc0KeCps7BQXzdUo=t3uqx=uz3SH6Nae44KgZQu+fzyhXg at mail dot gmail dot com>
Richard Biener <richard.guenther@gmail.com> writes:
> On Thu, Jun 25, 2015 at 10:15 AM, Richard Sandiford
>> Index: gcc/match.pd
>> ===================================================================
>> --- gcc/match.pd 2015-06-24 20:24:31.344998571 +0100
>> +++ gcc/match.pd 2015-06-24 20:24:31.340998617 +0100
>> @@ -1014,6 +1014,26 @@ along with GCC; see the file COPYING3.
>> (cnd (logical_inverted_value truth_valued_p@0) @1 @2)
>> (cnd @0 @2 @1)))
>>
>> +/* A + (B vcmp C ? 1 : 0) -> A - (B vcmp C), since vector comparisons
>> + return all-1 or all-0 results. */
>> +/* ??? We could instead convert all instances of the vec_cond to negate,
>> + but that isn't necessarily a win on its own. */
>> +(simplify
>> + (plus:c @3 (view_convert? (vec_cond @0 integer_each_onep@1 integer_zerop@2)))
>> + (if (VECTOR_TYPE_P (type)
>> + && TYPE_VECTOR_SUBPARTS (type) == TYPE_VECTOR_SUBPARTS (TREE_TYPE (@0))
>> + && (TYPE_MODE (TREE_TYPE (type))
>> + == TYPE_MODE (TREE_TYPE (TREE_TYPE (@0)))))
>> + (minus @3 (view_convert @0))))
>> +
>> +/* ... likewise A - (B vcmp C ? 1 : 0) -> A + (B vcmp C). */
>> +(simplify
>> + (minus @3 (view_convert? (vec_cond @0 integer_each_onep@1 integer_zerop@2)))
>> + (if (VECTOR_TYPE_P (type)
>> + && TYPE_VECTOR_SUBPARTS (type) == TYPE_VECTOR_SUBPARTS (TREE_TYPE (@0))
>> + && (TYPE_PRECISION (TREE_TYPE (type))
>> + == TYPE_PRECISION (TREE_TYPE (TREE_TYPE (@0)))))
>
> Either TYPE_PRECISION or TYPE_MODE please ;)
Bah. The main reason I hate cut-&-paste is that I'm so hopeless at it.
> I think that TYPE_MODE is more correct if you consider (minus V4SF
> (view_convert:V4SF (vec_cond V4SI V4SI V4SI)) where you would end up
> with a non-sensical TYPE_PRECISION query on V4SF. So probably
> VECTOR_INTEGER_TYPE_P again, then TYPE_PRECISION is good.
Actually, they were both meant to be TYPE_MODE, as below. Is this OK?
Thanks,
Richard
gcc/
* match.pd: Add patterns for vec_conds between 1 and 0.
gcc/testsuite/
* gcc.target/aarch64/vect-add-sub-cond.c: New test.
Index: gcc/match.pd
===================================================================
--- gcc/match.pd 2015-06-25 11:06:50.462827031 +0100
+++ gcc/match.pd 2015-06-25 11:07:23.742445798 +0100
@@ -1014,6 +1014,26 @@ along with GCC; see the file COPYING3.
(cnd (logical_inverted_value truth_valued_p@0) @1 @2)
(cnd @0 @2 @1)))
+/* A + (B vcmp C ? 1 : 0) -> A - (B vcmp C), since vector comparisons
+ return all-1 or all-0 results. */
+/* ??? We could instead convert all instances of the vec_cond to negate,
+ but that isn't necessarily a win on its own. */
+(simplify
+ (plus:c @3 (view_convert? (vec_cond @0 integer_each_onep@1 integer_zerop@2)))
+ (if (VECTOR_TYPE_P (type)
+ && TYPE_VECTOR_SUBPARTS (type) == TYPE_VECTOR_SUBPARTS (TREE_TYPE (@0))
+ && (TYPE_MODE (TREE_TYPE (type))
+ == TYPE_MODE (TREE_TYPE (TREE_TYPE (@0)))))
+ (minus @3 (view_convert @0))))
+
+/* ... likewise A - (B vcmp C ? 1 : 0) -> A + (B vcmp C). */
+(simplify
+ (minus @3 (view_convert? (vec_cond @0 integer_each_onep@1 integer_zerop@2)))
+ (if (VECTOR_TYPE_P (type)
+ && TYPE_VECTOR_SUBPARTS (type) == TYPE_VECTOR_SUBPARTS (TREE_TYPE (@0))
+ && (TYPE_MODE (TREE_TYPE (type))
+ == TYPE_MODE (TREE_TYPE (TREE_TYPE (@0)))))
+ (plus @3 (view_convert @0))))
/* Simplifications of comparisons. */
Index: gcc/testsuite/gcc.target/aarch64/vect-add-sub-cond.c
===================================================================
--- /dev/null 2015-06-02 17:27:28.541944012 +0100
+++ gcc/testsuite/gcc.target/aarch64/vect-add-sub-cond.c 2015-06-25 11:06:50.458827055 +0100
@@ -0,0 +1,94 @@
+/* Make sure that vector comaprison results are not unnecessarily ANDed
+ with vectors of 1. */
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize" } */
+
+#define COUNT1(X) if (X) count += 1
+#define COUNT2(X) if (X) count -= 1
+#define COUNT3(X) count += (X)
+#define COUNT4(X) count -= (X)
+
+#define COND1(X) (X)
+#define COND2(X) ((X) ? 1 : 0)
+#define COND3(X) ((X) ? -1 : 0)
+#define COND4(X) ((X) ? 0 : 1)
+#define COND5(X) ((X) ? 0 : -1)
+
+#define TEST_LT(X, Y) ((X) < (Y))
+#define TEST_LE(X, Y) ((X) <= (Y))
+#define TEST_GT(X, Y) ((X) > (Y))
+#define TEST_GE(X, Y) ((X) >= (Y))
+#define TEST_EQ(X, Y) ((X) == (Y))
+#define TEST_NE(X, Y) ((X) != (Y))
+
+#define COUNT_LOOP(ID, TYPE, CMP_ARRAY, TEST, COUNT) \
+ TYPE \
+ reduc_##ID (__typeof__ (CMP_ARRAY[0]) x) \
+ { \
+ TYPE count = 0; \
+ for (unsigned int i = 0; i < 1024; ++i) \
+ COUNT (TEST (CMP_ARRAY[i], x)); \
+ return count; \
+ }
+
+#define COND_LOOP(ID, ARRAY, CMP_ARRAY, TEST, COND) \
+ void \
+ plus_##ID (__typeof__ (CMP_ARRAY[0]) x) \
+ { \
+ for (unsigned int i = 0; i < 1024; ++i) \
+ ARRAY[i] += COND (TEST (CMP_ARRAY[i], x)); \
+ } \
+ void \
+ plusc_##ID (void) \
+ { \
+ for (unsigned int i = 0; i < 1024; ++i) \
+ ARRAY[i] += COND (TEST (CMP_ARRAY[i], 10)); \
+ } \
+ void \
+ minus_##ID (__typeof__ (CMP_ARRAY[0]) x) \
+ { \
+ for (unsigned int i = 0; i < 1024; ++i) \
+ ARRAY[i] -= COND (TEST (CMP_ARRAY[i], x)); \
+ } \
+ void \
+ minusc_##ID (void) \
+ { \
+ for (unsigned int i = 0; i < 1024; ++i) \
+ ARRAY[i] += COND (TEST (CMP_ARRAY[i], 1)); \
+ }
+
+#define ALL_LOOPS(ID, ARRAY, CMP_ARRAY, TEST) \
+ typedef __typeof__(ARRAY[0]) ID##_type; \
+ COUNT_LOOP (ID##_1, ID##_type, CMP_ARRAY, TEST, COUNT1) \
+ COUNT_LOOP (ID##_2, ID##_type, CMP_ARRAY, TEST, COUNT2) \
+ COUNT_LOOP (ID##_3, ID##_type, CMP_ARRAY, TEST, COUNT3) \
+ COUNT_LOOP (ID##_4, ID##_type, CMP_ARRAY, TEST, COUNT4) \
+ COND_LOOP (ID##_1, ARRAY, CMP_ARRAY, TEST, COND1) \
+ COND_LOOP (ID##_2, ARRAY, CMP_ARRAY, TEST, COND2) \
+ COND_LOOP (ID##_3, ARRAY, CMP_ARRAY, TEST, COND3) \
+ COND_LOOP (ID##_4, ARRAY, CMP_ARRAY, TEST, COND4) \
+ COND_LOOP (ID##_5, ARRAY, CMP_ARRAY, TEST, COND5)
+
+signed int asi[1024] __attribute__ ((aligned (16)));
+unsigned int aui[1024] __attribute__ ((aligned (16)));
+signed long long asl[1024] __attribute__ ((aligned (16)));
+unsigned long long aul[1024] __attribute__ ((aligned (16)));
+float af[1024] __attribute__ ((aligned (16)));
+double ad[1024] __attribute__ ((aligned (16)));
+
+ALL_LOOPS (si_si, aui, asi, TEST_LT)
+ALL_LOOPS (ui_si, aui, asi, TEST_LE)
+ALL_LOOPS (si_ui, aui, asi, TEST_GT)
+ALL_LOOPS (ui_ui, aui, asi, TEST_GE)
+ALL_LOOPS (sl_sl, asl, asl, TEST_NE)
+ALL_LOOPS (ul_ul, aul, aul, TEST_EQ)
+ALL_LOOPS (si_f, asi, af, TEST_LE)
+ALL_LOOPS (ui_f, aui, af, TEST_GT)
+ALL_LOOPS (sl_d, asl, ad, TEST_GE)
+ALL_LOOPS (ul_d, aul, ad, TEST_GT)
+
+/* { dg-final { scan-assembler-not "\tand\t" } } */
+/* { dg-final { scan-assembler-not "\tld\[^\t\]*\t\[wx\]" } } */
+/* { dg-final { scan-assembler-not "\tst\[^\t\]*\t\[wx\]" } } */
+/* { dg-final { scan-assembler "\tldr\tq" } } */
+/* { dg-final { scan-assembler "\tstr\tq" } } */