Hi,
three of remainings false positives of -Warray-bounds on -O3 bootstrap turned
out
to be bug in vectorizer. It sets the loop bound on prologue/epilogue to be
vectorization_factor - 1.
This is not correct: when vectorization_factor is 2, the epilogue/prologue
never loops, so number of iterations should be 0. Fixing this however led to
wrong code that turned out to be bug in vect_do_peeling_for_loop_bound.
With PEELING_FOR_GAPS we actually skip the last iteration of the vectorized
loop and thus the bound is vectorization_factor * 2 - 2.
Fixed thus, I also made the vectorizer to properly update loop bound
on the vectorized loop so it can be fully unrolled afterwards.
This hits on the testcase I derrived from ira.c where the loop iterates 27
times before vectorizing, while after vectorizing it can be fully unrolled
(our bound is 16) leading to quite nice code sequence.
Bootstrapped/regtested x86_64-linux, comitted as obvious.
Honza
* gcc.target/i386/l_fma_float_?.c: Update.
* gcc.target/i386/l_fma_double_?.c: Update.
* tree-vect-loop-manip.c (vect_do_peeling_for_loop_bound,
vect_do_peeling_for_alignment): Fix loop bound computation.
* tree-vect-loop.c (vect_transform_loop): Maintain loop bounds.
Index: tree-vect-loop.c
===================================================================
*** tree-vect-loop.c (revision 193174)
--- tree-vect-loop.c (working copy)
*************** vect_transform_loop (loop_vec_info loop_
*** 5448,5457 ****
--- 5448,5463 ----
bool transform_pattern_stmt = false;
bool check_profitability = false;
int th;
+ /* Record number of iterations before we started tampering with the
profile. */
+ gcov_type expected_iterations = expected_loop_iterations_unbounded (loop);
if (dump_enabled_p ())
dump_printf_loc (MSG_NOTE, vect_location, "=== vec_transform_loop ===");
+ /* If profile is inprecise, we have chance to fix it up. */
+ if (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo))
+ expected_iterations = LOOP_VINFO_INT_NITERS (loop_vinfo);
+
/* Use the more conservative vectorization threshold. If the number
of iterations is constant assume the cost check has been performed
by our caller. If the threshold makes all loops profitable that
*************** vect_transform_loop (loop_vec_info loop_
*** 5735,5740 ****
--- 5741,5765 ----
slpeel_make_loop_iterate_ntimes (loop, ratio);
+ /* Reduce loop iterations by the vectorization factor. */
+ scale_loop_profile (loop, RDIV (REG_BR_PROB_BASE , vectorization_factor),
+ expected_iterations / vectorization_factor);
+ loop->nb_iterations_upper_bound
+ = loop->nb_iterations_upper_bound.udiv (double_int::from_uhwi
(vectorization_factor),
+ FLOOR_DIV_EXPR);
+ if (LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo)
+ && loop->nb_iterations_upper_bound != double_int_zero)
+ loop->nb_iterations_upper_bound = loop->nb_iterations_upper_bound -
double_int_one;
+ if (loop->any_estimate)
+ {
+ loop->nb_iterations_estimate
+ = loop->nb_iterations_estimate.udiv (double_int::from_uhwi
(vectorization_factor),
+ FLOOR_DIV_EXPR);
+ if (LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo)
+ && loop->nb_iterations_estimate != double_int_zero)
+ loop->nb_iterations_estimate = loop->nb_iterations_estimate -
double_int_one;
+ }
+
/* The memory tags and pointers in vectorized statements need to
have their SSA forms updated. FIXME, why can't this be delayed
until all the loops have been transformed? */
Index: tree-vect-loop-manip.c
===================================================================
*** tree-vect-loop-manip.c (revision 193174)
--- tree-vect-loop-manip.c (working copy)
*************** vect_do_peeling_for_loop_bound (loop_vec
*** 1954,1962 ****
by ratio_mult_vf_name steps. */
vect_update_ivs_after_vectorizer (loop_vinfo, ratio_mult_vf_name, update_e);
! max_iter = LOOP_VINFO_VECT_FACTOR (loop_vinfo) - 1;
if (check_profitability)
! max_iter = MAX (max_iter, (int) th);
record_niter_bound (new_loop, double_int::from_shwi (max_iter), false,
true);
dump_printf (MSG_OPTIMIZED_LOCATIONS,
"Setting upper bound of nb iterations for epilogue "
--- 1954,1969 ----
by ratio_mult_vf_name steps. */
vect_update_ivs_after_vectorizer (loop_vinfo, ratio_mult_vf_name, update_e);
! /* For vectorization factor N, we need to copy last N-1 values in epilogue
! and this means N-2 loopback edge executions.
!
! PEELING_FOR_GAPS works by subtracting last iteration and thus the
epilogue
! will execute at least LOOP_VINFO_VECT_FACTOR times. */
! max_iter = (LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo)
! ? LOOP_VINFO_VECT_FACTOR (loop_vinfo) * 2
! : LOOP_VINFO_VECT_FACTOR (loop_vinfo)) - 2;
if (check_profitability)
! max_iter = MAX (max_iter, (int) th - 1);
record_niter_bound (new_loop, double_int::from_shwi (max_iter), false,
true);
dump_printf (MSG_OPTIMIZED_LOCATIONS,
"Setting upper bound of nb iterations for epilogue "
*************** vect_do_peeling_for_alignment (loop_vec_
*** 2186,2194 ****
#ifdef ENABLE_CHECKING
slpeel_verify_cfg_after_peeling (new_loop, loop);
#endif
! max_iter = LOOP_VINFO_VECT_FACTOR (loop_vinfo) - 1;
if (check_profitability)
! max_iter = MAX (max_iter, (int) th);
record_niter_bound (new_loop, double_int::from_shwi (max_iter), false,
true);
dump_printf (MSG_OPTIMIZED_LOCATIONS,
"Setting upper bound of nb iterations for prologue "
--- 2193,2203 ----
#ifdef ENABLE_CHECKING
slpeel_verify_cfg_after_peeling (new_loop, loop);
#endif
! /* For vectorization factor N, we need to copy at most N-1 values
! for alignment and this means N-2 loopback edge executions. */
! max_iter = LOOP_VINFO_VECT_FACTOR (loop_vinfo) - 2;
if (check_profitability)
! max_iter = MAX (max_iter, (int) th - 1);
record_niter_bound (new_loop, double_int::from_shwi (max_iter), false,
true);
dump_printf (MSG_OPTIMIZED_LOCATIONS,
"Setting upper bound of nb iterations for prologue "
Index: testsuite/gcc.target/i386/l_fma_float_5.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_float_5.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_float_5.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 72 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 64 } } */
Index: testsuite/gcc.target/i386/l_fma_double_4.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_double_4.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_double_4.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 40 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 32 } } */
Index: testsuite/gcc.target/i386/l_fma_float_2.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_float_2.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_float_2.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 72 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 64 } } */
Index: testsuite/gcc.target/i386/l_fma_float_6.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_float_6.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_float_6.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 72 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 64 } } */
Index: testsuite/gcc.target/i386/l_fma_double_1.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_double_1.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_double_1.c (working copy)
***************
*** 16,26 ****
/* { dg-final { scan-assembler-times "vfnmadd231pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231pd" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfmadd213sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfmsub213sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213sd" 20 } } */
--- 16,26 ----
/* { dg-final { scan-assembler-times "vfnmadd231pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231pd" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfmadd213sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfmsub213sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213sd" 16 } } */
Index: testsuite/gcc.target/i386/l_fma_double_5.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_double_5.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_double_5.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 40 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 32 } } */
Index: testsuite/gcc.target/i386/l_fma_float_3.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_float_3.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_float_3.c (working copy)
***************
*** 16,26 ****
/* { dg-final { scan-assembler-times "vfnmadd231ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231ps" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfmadd213ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfmsub213ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213ss" 36 } } */
--- 16,26 ----
/* { dg-final { scan-assembler-times "vfnmadd231ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231ps" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfmadd213ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub213ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213ss" 32 } } */
Index: testsuite/gcc.target/i386/l_fma_double_2.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_double_2.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_double_2.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 40 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 32 } } */
Index: testsuite/gcc.target/i386/l_fma_double_6.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_double_6.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_double_6.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 40 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 40 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132pd" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 32 } } */
Index: testsuite/gcc.target/i386/l_fma_float_4.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_float_4.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_float_4.c (working copy)
***************
*** 12,18 ****
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 72 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 72 } } */
--- 12,18 ----
/* { dg-final { scan-assembler-times "vfmsub132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmadd132ps" 8 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 8 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 64 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 64 } } */
Index: testsuite/gcc.target/i386/l_fma_double_3.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_double_3.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_double_3.c (working copy)
***************
*** 16,26 ****
/* { dg-final { scan-assembler-times "vfnmadd231pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231pd" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfmadd213sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfmsub213sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 20 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213sd" 20 } } */
--- 16,26 ----
/* { dg-final { scan-assembler-times "vfnmadd231pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132pd" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231pd" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfmadd213sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfmsub132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfmsub213sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132sd" 16 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213sd" 16 } } */
Index: testsuite/gcc.target/i386/l_fma_float_1.c
===================================================================
*** testsuite/gcc.target/i386/l_fma_float_1.c (revision 193174)
--- testsuite/gcc.target/i386/l_fma_float_1.c (working copy)
***************
*** 16,26 ****
/* { dg-final { scan-assembler-times "vfnmadd231ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231ps" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfmadd213ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfmsub213ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 36 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213ss" 36 } } */
--- 16,26 ----
/* { dg-final { scan-assembler-times "vfnmadd231ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub132ps" 4 } } */
/* { dg-final { scan-assembler-times "vfnmsub231ps" 4 } } */
! /* { dg-final { scan-assembler-times "vfmadd132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfmadd213ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfmsub213ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmadd213ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub132ss" 32 } } */
! /* { dg-final { scan-assembler-times "vfnmsub213ss" 32 } } */
