diff options
| author | Andreas Krebbel <krebbel@linux.ibm.com> | 2018-08-06 15:01:00 +0000 |
|---|---|---|
| committer | Andreas Krebbel <krebbel@gcc.gnu.org> | 2018-08-06 15:01:00 +0000 |
| commit | 8eed4721de54c66953af83791db19d75dd23bce8 (patch) | |
| tree | bcd08467fe566c274f0bdc073ae37165288290b7 /gcc | |
| parent | 2f171da9ccea4fc9c7918e22e6485b49626f8730 (diff) | |
| download | gcc-8eed4721de54c66953af83791db19d75dd23bce8.zip gcc-8eed4721de54c66953af83791db19d75dd23bce8.tar.gz gcc-8eed4721de54c66953af83791db19d75dd23bce8.tar.bz2 | |
S/390: Don't unroll memory blk op loops
gcc/ChangeLog:
2018-08-06 Andreas Krebbel <krebbel@linux.ibm.com>
* config/s390/s390.c (s390_loop_unroll_adjust): Prevent small
loops with memory block operations from getting unrolled.
gcc/testsuite/ChangeLog:
2018-08-06 Andreas Krebbel <krebbel@linux.ibm.com>
* gcc.target/s390/nomemloopunroll-1.c: New test.
From-SVN: r263336
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/ChangeLog | 5 | ||||
| -rw-r--r-- | gcc/config/s390/s390.c | 31 | ||||
| -rw-r--r-- | gcc/testsuite/ChangeLog | 4 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.target/s390/nomemloopunroll-1.c | 27 |
4 files changed, 64 insertions, 3 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index c36cffa..b15d546 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,8 @@ +2018-08-06 Andreas Krebbel <krebbel@linux.ibm.com> + + * config/s390/s390.c (s390_loop_unroll_adjust): Prevent small + loops with memory block operations from getting unrolled. + 2018-08-06 Ulrich Weigand <uweigand@de.ibm.com> PR target/86807 diff --git a/gcc/config/s390/s390.c b/gcc/config/s390/s390.c index ec588a2..aa34f56 100644 --- a/gcc/config/s390/s390.c +++ b/gcc/config/s390/s390.c @@ -390,6 +390,11 @@ static unsigned vfu_longrunning[NUM_SIDES]; base and index are registers of the class ADDR_REGS, displacement is an unsigned 12-bit immediate constant. */ +/* The max number of insns of backend generated memset/memcpy/memcmp + loops. This value is used in the unroll adjust hook to detect such + loops. Current max is 9 coming from the memcmp loop. */ +#define BLOCK_MEM_OPS_LOOP_INSNS 9 + struct s390_address { rtx base; @@ -15385,9 +15390,29 @@ s390_loop_unroll_adjust (unsigned nunroll, struct loop *loop) for (i = 0; i < loop->num_nodes; i++) FOR_BB_INSNS (bbs[i], insn) if (INSN_P (insn) && INSN_CODE (insn) != -1) - FOR_EACH_SUBRTX (iter, array, PATTERN (insn), NONCONST) - if (MEM_P (*iter)) - mem_count += 1; + { + rtx set; + + /* The runtime of small loops with memory block operations + will be determined by the memory operation. Doing + unrolling doesn't help here. Measurements to confirm + this where only done on recent CPU levels. So better do + not change anything for older CPUs. */ + if (s390_tune >= PROCESSOR_2964_Z13 + && loop->ninsns <= BLOCK_MEM_OPS_LOOP_INSNS + && ((set = single_set (insn)) != NULL_RTX) + && ((GET_MODE (SET_DEST (set)) == BLKmode + && (GET_MODE (SET_SRC (set)) == BLKmode + || SET_SRC (set) == const0_rtx)) + || (GET_CODE (SET_SRC (set)) == COMPARE + && GET_MODE (XEXP (SET_SRC (set), 0)) == BLKmode + && GET_MODE (XEXP (SET_SRC (set), 1)) == BLKmode))) + return 1; + + FOR_EACH_SUBRTX (iter, array, PATTERN (insn), NONCONST) + if (MEM_P (*iter)) + mem_count += 1; + } free (bbs); /* Prevent division by zero, and we do not need to adjust nunroll in this case. */ diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index fb65bd0..0d8fc74 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,7 @@ +2018-08-06 Andreas Krebbel <krebbel@linux.ibm.com> + + * gcc.target/s390/nomemloopunroll-1.c: New test. + 2018-08-05 H.J. Lu <hongjiu.lu@intel.com> PR target/86386 diff --git a/gcc/testsuite/gcc.target/s390/nomemloopunroll-1.c b/gcc/testsuite/gcc.target/s390/nomemloopunroll-1.c new file mode 100644 index 0000000..695d925 --- /dev/null +++ b/gcc/testsuite/gcc.target/s390/nomemloopunroll-1.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-O3 -funroll-loops -march=z13" } */ + +/* 2x mvc */ +void * +foo (char *a, int c, long len) +{ + return __builtin_memset (a, c, len); +} + +/* 2x mvc */ +void +bar (char *a, char *b) +{ + __builtin_memcpy (a, b, 30000); +} + +/* 2x clc */ + +int +baz (char *a, char *b) +{ + return __builtin_memcmp (a, b, 30000); +} + +/* { dg-final { scan-assembler-times "\\\smvc\\\s" 4 } } */ +/* { dg-final { scan-assembler-times "\\\sclc\\\s" 2 } } */ |