@@ -1392,7 +1392,7 @@ DEFPARAM (PARAM_MAX_VRP_SWITCH_ASSERTIONS,
DEFPARAM (PARAM_VECT_EPILOGUES_NOMASK,
"vect-epilogues-nomask",
"Enable loop epilogue vectorization using smaller vector size.",
- 0, 0, 1)
+ 1, 0, 1)
DEFPARAM(PARAM_UNROLL_JAM_MIN_PERCENT,
"unroll-jam-min-percent",
@@ -95,4 +95,4 @@ main ()
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 4 "vect" { target { vect_call_copysignf && vect_call_sqrtf } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 3 "vect" { target { vect_call_copysignf && vect_call_sqrtf } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 4 "vect" { target { vect_call_copysignf && vect_call_sqrtf } } } } */
@@ -34,4 +34,4 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times {using an in-order \(fold-left\) reduction} 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times {using an in-order \(fold-left\) reduction} 2 "vect" } } */
@@ -37,5 +37,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_int_min_max } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail vect_no_int_min_max } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { xfail vect_no_int_min_max } } } */
@@ -75,5 +75,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 1 "vect" { target vect_widen_mult_hi_to_si } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED." 2 "vect" { target vect_widen_mult_hi_to_si } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" } } */
@@ -28,4 +28,4 @@ unsigned int main1 ()
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_sum_hi_to_si } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 1 "vect" { target vect_widen_sum_hi_to_si } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 2 "vect" { target vect_widen_sum_hi_to_si } } } */
@@ -93,5 +93,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 4 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" { xfail vect_element_align_preferred } } } */
@@ -90,5 +90,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 3 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" { xfail vect_element_align_preferred } } } */
@@ -78,6 +78,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 3 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { {! vect_aligned_arrays} && {vect_sizes_32B_16B} } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { {vect_aligned_arrays} && {! vect_sizes_32B_16B} } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { {vect_aligned_arrays} && {! vect_sizes_32B_16B} } } } } */
@@ -90,5 +90,5 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 4 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" { target { {! vect_aligned_arrays} && {vect_sizes_32B_16B} } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { {vect_aligned_arrays} && {! vect_sizes_32B_16B} } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 8 "vect" { target { {! vect_aligned_arrays} && {vect_sizes_32B_16B} } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" { target { {vect_aligned_arrays} && {! vect_sizes_32B_16B} } } } } */
@@ -51,5 +51,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "dependence distance negative" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "dependence distance negative" 2 "vect" } } */
@@ -51,4 +51,4 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "dependence distance negative" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "dependence distance negative" 2 "vect" } } */
@@ -183,4 +183,4 @@ int main ()
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 4 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "dependence distance negative" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "dependence distance negative" 8 "vect" } } */
@@ -73,5 +73,5 @@ int main ()
/* The initialization induction loop (with aligned access) is also vectorized. */
/* { dg-final { scan-tree-dump-times "vectorized 3 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 2 "vect" { target { { vect_aligned_arrays } && {! vect_sizes_32B_16B} } } } } */
-/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 1 "vect" { target { {! vect_aligned_arrays } && {vect_sizes_32B_16B} } } } } */
+/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 4 "vect" { target { { vect_aligned_arrays } && {! vect_sizes_32B_16B} } } } } */
+/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 2 "vect" { target { {! vect_aligned_arrays } && {vect_sizes_32B_16B} } } } } */
@@ -12,4 +12,4 @@ void f(unsigned char *s, unsigned char *d, int n) {
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
@@ -16,6 +16,6 @@ foo (int integral, int decimal, int power_ten)
/* We can avoid a scalar tail when using fully-masked loops with a fixed
vector length. */
-/* { dg-final { scan-tree-dump-times "\\* 10" 2 "optimized" { target { { ! vect_fully_masked } || vect_variable_length } } } } */
+/* { dg-final { scan-tree-dump-times "\\* 10" 0 "optimized" { target { { ! vect_fully_masked } || vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "\\* 10" 0 "optimized" { target { vect_fully_masked && { ! vect_variable_length } } } } } */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
int posix_memalign(void **memptr, __SIZE_TYPE__ alignment, __SIZE_TYPE__ size);
void bar (int *);
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
void bar (int *);
@@ -40,6 +40,6 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 4 "vect" { target vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 4 "vect" { target { ! vect_fold_extract_last } } } } */
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 8 "vect" } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 8 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 8 "vect" { target { ! vect_fold_extract_last } } } } */
@@ -40,6 +40,6 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" } } */
-/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 4 "vect" { xfail vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 4 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 8 "vect" } } */
+/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 8 "vect" { xfail vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 8 "vect" { target vect_fold_extract_last } } } */
@@ -40,6 +40,6 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 4 "vect" { target vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 4 "vect" { target { ! vect_fold_extract_last } } } } */
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 8 "vect" } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 8 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 8 "vect" { target { ! vect_fold_extract_last } } } } */
@@ -40,7 +40,7 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 4 "vect" { target vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 4 "vect" { target { ! vect_fold_extract_last } } } } */
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 8 "vect" } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 8 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 8 "vect" { target { ! vect_fold_extract_last } } } } */
@@ -72,5 +72,5 @@ main ()
}
/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 5 "vect" { target vect_condition } } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 10 "vect" { target vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 10 "vect" { target { { ! vect_fold_extract_last } && vect_condition } } } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 15 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 5 "vect" { target { { ! vect_fold_extract_last } && vect_condition } } } } */
@@ -72,5 +72,5 @@ main ()
}
/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 5 "vect" { target vect_condition } } } */
-/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 10 "vect" { target vect_condition xfail vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 10 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 15 "vect" { target vect_condition xfail vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 5 "vect" { target vect_fold_extract_last } } } */
@@ -56,5 +56,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { { ! vect_unaligned_possible } || { ! vect_natural_alignment } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" { xfail { { ! vect_unaligned_possible } || { ! vect_natural_alignment } } } } } */
@@ -38,5 +38,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_int_add } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail vect_no_int_add } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { xfail vect_no_int_add } } } */
@@ -43,5 +43,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail vect_no_int_min_max } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail vect_no_int_min_max } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { xfail vect_no_int_min_max } } } */
@@ -43,6 +43,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail { vect_no_int_add || { ! { vect_unpack || vect_strided2 } } } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "different interleaving chains in one node" 1 "vect" { target { ! vect_no_int_add } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "different interleaving chains in one node" 2 "vect" { target { ! vect_no_int_add } } } } */
@@ -2,6 +2,7 @@
/* { dg-require-effective-target vect_usad_char } */
/* With AVX256 or more we do not pull off the trick eliding the epilogue. */
/* { dg-additional-options "-mprefer-avx128" { target { x86_64-*-* i?86-*-* } } } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
typedef unsigned char uint8_t;
int x264_pixel_sad_8x8( uint8_t *pix1, uint8_t *pix2, int i_stride_pix2 )
@@ -47,6 +47,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_mult_hi_to_si } } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target vect_widen_mult_hi_to_si } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
-/* { dg-final { scan-tree-dump-times "pattern recognized" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 4 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "pattern recognized" 5 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
@@ -48,6 +48,6 @@ int main (void)
/* We can't handle the first loop with variable-length vectors and so
fall back to the fixed-length mininum instead. */
-/* { dg-final { scan-tree-dump-times "Detected reduction\\." 3 "vect" { xfail vect_variable_length } } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction\\." 6 "vect" { xfail vect_variable_length } } } */
/* { dg-final { scan-tree-dump-times "vectorized 3 loops" 1 "vect" { target { ! vect_no_int_min_max } } } } */
-/* { dg-final { scan-tree-dump-times {using an in-order \(fold-left\) reduction} 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times {using an in-order \(fold-left\) reduction} 2 "vect" } } */
@@ -56,5 +56,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "accesses have the same alignment" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "accesses have the same alignment" 2 "vect" } } */
@@ -75,6 +75,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target vect_element_align } } } */
-/* { dg-final { scan-tree-dump-times "not vectorized: unsupported unaligned store" 2 "vect" { xfail vect_element_align } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { target vect_element_align xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "not vectorized: unsupported unaligned store" 6 "vect" { xfail vect_element_align } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" { target vect_element_align xfail { ! vect_unaligned_possible } } } } */
@@ -25,4 +25,4 @@ unsigned int foo (const unsigned int x[OUTER][INNER][2])
return sum;
}
-/* { dg-final { scan-tree-dump-times "Detected interleaving load of size 2" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Detected interleaving load of size 2" 2 "vect" } } */
@@ -36,5 +36,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" { xfail { ! vect_align_stack_vars } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_element_align_preferred || { ! vect_align_stack_vars } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_align_stack_vars } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { vect_element_align_preferred || { ! vect_align_stack_vars } } } } } */
@@ -46,5 +46,5 @@ int main (void)
/* The initialization induction loop (with aligned access) is also vectorized. */
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_unaligned_possible } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
@@ -51,6 +51,6 @@ int main (void)
/* The initialization induction loop (with aligned access) is also vectorized. */
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" {target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" {target { vect_no_align && { ! vect_hw_misalign } } } } } */
@@ -64,8 +64,8 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { { ! vector_alignment_reachable } && { ! vect_element_align } } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { xfail { vect_no_align || { { ! vector_alignment_reachable } || vect_element_align } } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { target vect_element_align xfail { ! { vect_unaligned_possible && vect_align_stack_vars } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_no_align || { { ! vector_alignment_reachable } || vect_element_align } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 6 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target { { ! vector_alignment_reachable } && { ! vect_element_align } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 8 "vect" { xfail { vect_no_align || { { ! vector_alignment_reachable } || vect_element_align } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" { target vect_element_align xfail { ! { vect_unaligned_possible && vect_align_stack_vars } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { vect_no_align || { { ! vector_alignment_reachable } || vect_element_align } } } } } */
@@ -65,7 +65,7 @@ int main (void)
two loads to be aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" { xfail { ! vect_unaligned_possible } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable} } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { {! vector_alignment_reachable} && {{! vect_no_align} && {! vect_hw_misalign} } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 6 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { {! vector_alignment_reachable} && {{! vect_no_align} && {! vect_hw_misalign} } } } } } */
@@ -1,5 +1,6 @@
/* { dg-require-effective-target vect_float } */
/* { dg-add-options double_vectors } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include <stdarg.h>
#include "tree-vect.h"
@@ -55,7 +55,7 @@ int main (void)
(The store is aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 4 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
@@ -61,7 +61,7 @@ int main (void)
align the store will not force the two loads to be aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" { xfail { ! vect_unaligned_possible } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { xfail { { vect_no_align && { ! vect_hw_misalign } } || {! vector_alignment_reachable} } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { {! vector_alignment_reachable} && { {! vect_no_align } && {! vect_hw_misalign } } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 6 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { {! vector_alignment_reachable} && { {! vect_no_align } && {! vect_hw_misalign } } } } } } */
@@ -56,7 +56,7 @@ int main (void)
(The store is aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 4 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
@@ -60,5 +60,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" { xfail { ! vect_align_stack_vars } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_align_stack_vars } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail vect_element_align_preferred } } } */
@@ -69,6 +69,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { ! vect_element_align } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { vect_element_align } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { target { { ! vect_element_align } || vect_element_align_preferred} } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { vect_element_align && { ! vect_element_align_preferred } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { vect_element_align } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { { ! vect_element_align } || vect_element_align_preferred} } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { vect_element_align && { ! vect_element_align_preferred } } } } } */
@@ -58,5 +58,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail vect_element_align_preferred } } } */
@@ -70,6 +70,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { ! vect_element_align } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { vect_element_align } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { target { { ! vect_element_align } || vect_element_align_preferred } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { vect_element_align && { ! vect_element_align_preferred } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { vect_element_align } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { { ! vect_element_align } || vect_element_align_preferred } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { target { vect_element_align && { ! vect_element_align_preferred } } } } } */
@@ -48,5 +48,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_unaligned_possible } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
@@ -49,6 +49,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
@@ -49,6 +49,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
@@ -54,8 +54,8 @@ int main (void)
both for the load and the store. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { {! vect_no_align} && { unaligned_stack && vector_alignment_reachable } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { {! unaligned_stack} && { vect_no_align && { ! vect_hw_misalign } } } || {unaligned_stack && { {! vector_alignment_reachable} && {! vect_no_align } } } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { { unaligned_stack && { vector_alignment_reachable && vect_no_align } } || {unaligned_stack && { {! vector_alignment_reachable} && vect_no_align } } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" { target { {! vect_no_align} && { unaligned_stack && vector_alignment_reachable } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 4 "vect" { target { { {! unaligned_stack} && { vect_no_align && { ! vect_hw_misalign } } } || {unaligned_stack && { {! vector_alignment_reachable} && {! vect_no_align } } } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 4 "vect" { target { { unaligned_stack && { vector_alignment_reachable && vect_no_align } } || {unaligned_stack && { {! vector_alignment_reachable} && vect_no_align } } } } } } */
@@ -48,6 +48,6 @@ int main (void)
/* Requires versioning for aliasing. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
@@ -55,8 +55,8 @@ int main (void)
both for the load and the store. */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { {! vect_no_align} && { unaligned_stack && vector_alignment_reachable } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { {! unaligned_stack} && { vect_no_align && { ! vect_hw_misalign } } } || {unaligned_stack && { {! vector_alignment_reachable} && { ! vect_no_align } } } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { { unaligned_stack && { vector_alignment_reachable && vect_no_align } } || {unaligned_stack && { {! vector_alignment_reachable} && vect_no_align } } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target vect_align_stack_vars xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target { ! vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 4 "vect" { target { {! vect_no_align} && { unaligned_stack && vector_alignment_reachable } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 4 "vect" { target { { {! unaligned_stack} && { vect_no_align && { ! vect_hw_misalign } } } || {unaligned_stack && { {! vector_alignment_reachable} && { ! vect_no_align } } } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 4 "vect" { target { { unaligned_stack && { vector_alignment_reachable && vect_no_align } } || {unaligned_stack && { {! vector_alignment_reachable} && vect_no_align } } } } } } */
@@ -48,6 +48,6 @@ int main (void)
(The store is aligned). */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
@@ -1,5 +1,6 @@
/* { dg-require-effective-target vect_int } */
/* { dg-add-options bind_pic_locally } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include <stdarg.h>
#include "tree-vect.h"
@@ -45,5 +45,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" { xfail { ! vect_align_stack_vars } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_element_align_preferred || { ! vect_align_stack_vars } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_align_stack_vars } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { vect_element_align_preferred || { ! vect_align_stack_vars } } } } } */
@@ -49,5 +49,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" { xfail { ! vect_align_stack_vars } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { vect_element_align_preferred || { ! vect_align_stack_vars } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_align_stack_vars } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { vect_element_align_preferred || { ! vect_align_stack_vars } } } } } */
@@ -66,6 +66,6 @@ main3 ()
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 3 "vect" { xfail vect_no_int_add } } } */
-/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 3 "vect" { target { { vect_aligned_arrays } && {! vect_sizes_32B_16B} } } } } */
-/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 2 "vect" { target { {! vect_aligned_arrays } && {vect_sizes_32B_16B} } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" {target { {! vector_alignment_reachable} && {! vect_hw_misalign} } } } } */
+/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 6 "vect" { target { { vect_aligned_arrays } && {! vect_sizes_32B_16B} } } } } */
+/* { dg-final { scan-tree-dump-times "accesses have the same alignment." 4 "vect" { target { {! vect_aligned_arrays } && {vect_sizes_32B_16B} } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 6 "vect" {target { {! vector_alignment_reachable} && {! vect_hw_misalign} } } } } */
@@ -97,5 +97,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 3 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 0 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 3 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 6 "vect" { xfail vect_element_align_preferred } } } */
@@ -49,6 +49,6 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { { {! vect_no_align} && vector_alignment_reachable } && { ! vect_align_stack_vars } } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { { {! vect_no_align} && vector_alignment_reachable } && vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { vect_no_align } || { { ! vector_alignment_reachable} || vect_element_align } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 1 "vect" { target { { vect_no_align && { ! vect_hw_misalign } } || { {! vector_alignment_reachable} && {! vect_element_align} } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { { {! vect_no_align} && vector_alignment_reachable } && vect_align_stack_vars } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { { vect_no_align } || { { ! vector_alignment_reachable} || vect_element_align } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning." 2 "vect" { target { { vect_no_align && { ! vect_hw_misalign } } || { {! vector_alignment_reachable} && {! vect_element_align} } } } } } */
@@ -14,6 +14,6 @@ f1 (struct s *a, struct s *b)
a->x[i + GAP] += b->x[i];
}
-/* { dg-final { scan-tree-dump-times "consider run-time aliasing" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "improved number of alias checks from 1 to 0" 1 "vect" { xfail vect_variable_length } } } */
-/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "consider run-time aliasing" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "improved number of alias checks from 1 to 0" 2 "vect" { xfail vect_variable_length } } } */
+/* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" } } */
@@ -1,5 +1,6 @@
/* { dg-require-effective-target vect_int } */
/* { dg-additional-options "-fno-tree-scev-cprop" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "tree-vect.h"
@@ -55,4 +55,4 @@ main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 2 "vect" } } */
@@ -1,4 +1,5 @@
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "tree-vect.h"
@@ -1,4 +1,5 @@
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "tree-vect.h"
@@ -68,5 +68,5 @@ main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 4 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 4 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 8 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 8 "vect" } } */
@@ -1,5 +1,6 @@
/* { dg-require-effective-target vect_int } */
/* { dg-additional-options "-fno-tree-scev-cprop" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "tree-vect.h"
@@ -69,5 +69,5 @@ main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 4 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 4 "vect" { xfail vect_variable_length } } } */
-/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 8 "vect" { xfail vect_variable_length } } } */
+/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 8 "vect" } } */
@@ -89,6 +89,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { { ! vect_unaligned_possible } || vect_sizes_32B_16B } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target { vect_no_align && { { ! vect_hw_misalign } && vect_sizes_32B_16B } } }} } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 8 "vect" { xfail { { ! vect_unaligned_possible } || vect_sizes_32B_16B } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 8 "vect" { target { vect_no_align && { { ! vect_hw_misalign } && vect_sizes_32B_16B } } }} } */
@@ -58,6 +58,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 3 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 3 "vect" { xfail { ! { vect_unaligned_possible && vect_align_stack_vars } } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using versioning" 6 "vect" { target { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 6 "vect" { xfail { ! { vect_unaligned_possible && vect_align_stack_vars } } } } } */
@@ -93,8 +93,8 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" { target { vect_element_align} } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { vect_no_align || vect_element_align } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 8 "vect" { target { vect_element_align} } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 8 "vect" { xfail { vect_no_align || vect_element_align } } } } */
/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 8 "vect" { target { ! vect_element_align } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 4 "vect" { target { vect_element_align } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 8 "vect" { target { vect_element_align } xfail { ! vect_unaligned_possible } } } } */
@@ -1,5 +1,6 @@
/* { dg-require-effective-target vect_int } */
/* { dg-add-options double_vectors } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include <stdarg.h>
#include "tree-vect.h"
@@ -48,5 +48,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "step doesn't divide the vector alignment" 1 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "step doesn't divide the vector alignment" 2 "vect" { xfail vect_element_align_preferred } } } */
@@ -48,5 +48,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "step doesn't divide the vector alignment" 1 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "step doesn't divide the vector alignment" 2 "vect" { xfail vect_element_align_preferred } } } */
@@ -50,5 +50,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "zero step in outer loop." 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "zero step in outer loop." 2 "vect" } } */
@@ -23,5 +23,5 @@ foo (){
}
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" { target { vect_short_mult && { ! vect_no_align } } } } } */
-/* { dg-final { scan-tree-dump-times "zero step in outer loop." 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" { target { vect_short_mult && { ! vect_no_align } } } } } */
+/* { dg-final { scan-tree-dump-times "zero step in outer loop." 2 "vect" } } */
@@ -60,5 +60,5 @@ int main ()
return 0;
}
-/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "zero step in outer loop." 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "OUTER LOOP VECTORIZED" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "zero step in outer loop." 2 "vect" } } */
@@ -48,5 +48,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { { vect_element_align } && { vect_aligned_arrays } } xfail { ! vect_unaligned_possible } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail vect_element_align_preferred } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { target { { vect_element_align } && { vect_aligned_arrays } } xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail vect_element_align_preferred } } } */
@@ -49,5 +49,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { target { { vect_element_align } && { vect_aligned_arrays } } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 7 "vect" { target { { vect_element_align } && { vect_aligned_arrays } } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { target { { vect_element_align } && { vect_aligned_arrays } } } } } */
@@ -61,5 +61,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { { ! vect_unaligned_possible } || vect_sizes_32B_16B } } } } */
-/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 1 "vect" { xfail { { ! vect_unaligned_possible } || vect_sizes_32B_16B } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { { ! vect_unaligned_possible } || vect_sizes_32B_16B } } } } */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { { ! vect_unaligned_possible } || vect_sizes_32B_16B } } } } */
@@ -46,5 +46,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 1 "vect" { xfail { ! vect_unaligned_possible } } } } */
+/* { dg-final { scan-tree-dump-times "Vectorizing an unaligned access" 2 "vect" { xfail { ! vect_unaligned_possible } } } } */
/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 0 "vect" } } */
@@ -49,5 +49,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times {using an in-order \(fold-left\) reduction} 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times {using an in-order \(fold-left\) reduction} 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
@@ -49,7 +49,7 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_sdot_hi } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_mult_hi_to_si } } } */
@@ -53,8 +53,8 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_sdot_qi } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_mult_qi_to_hi && vect_widen_sum_hi_to_si } } } } */
@@ -44,6 +44,6 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_pack_trunc || vect_udot_hi } } } } */
@@ -51,7 +51,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_udot_qi } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_mult_qi_to_hi && vect_widen_sum_qi_to_si } } } } */
@@ -43,7 +43,7 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 2 "vect" } } */
/* When the vectorizer is enhanced to vectorize accumulation into short for
targets that support accumulation into int (powerpc, ia64) we'd have:
@@ -39,6 +39,6 @@ main (void)
return foo ();
}
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_sum_hi_to_si } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { ! vect_widen_sum_hi_to_si } } } } */
@@ -39,6 +39,6 @@ main (void)
return foo ();
}
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_sum_qi_to_si || vect_unpack } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { { ! vect_widen_sum_qi_to_si } && { ! vect_unpack } } } } } */
@@ -39,6 +39,6 @@ main (void)
return foo ();
}
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_sum_qi_to_hi } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { ! vect_widen_sum_qi_to_hi } } } } */
@@ -39,6 +39,6 @@ main (void)
return foo ();
}
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_sum_hi_to_si } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { ! vect_widen_sum_hi_to_si } } } } */
@@ -40,6 +40,6 @@ main (void)
return foo ();
}
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_sum_pattern: detected" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_sum_qi_to_si && vect_unpack } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 0 "vect" { target { { ! vect_widen_sum_qi_to_si } && { ! vect_unpack } } } } } */
@@ -56,6 +56,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target vect_widen_mult_hi_to_si } } } */
-/* { dg-final { scan-tree-dump-times {vect_recog_widen_mult_pattern: detected:[^\n]* 2333} 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times {vect_recog_widen_mult_pattern: detected:[^\n]* 2333} 4 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
/* { dg-final { scan-tree-dump-times {widen_mult pattern recognized:[^\n]* 2333} 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
@@ -73,5 +73,5 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 3 "vect" { target vect_widen_mult_hi_to_si } } } */
-/* { dg-final { scan-tree-dump-times {vect_recog_widen_mult_pattern: detected:[^\n]* 2333} 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
-/* { dg-final { scan-tree-dump-times {widen_mult pattern recognized:[^\n]* = \(int\)} 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times {vect_recog_widen_mult_pattern: detected:[^\n]* 2333} 4 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times {widen_mult pattern recognized:[^\n]* = \(int\)} 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
@@ -55,6 +55,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target vect_widen_mult_hi_to_si } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
-/* { dg-final { scan-tree-dump-times "pattern recognized" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 4 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "pattern recognized" 4 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
@@ -44,6 +44,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_mult_hi_to_si } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
-/* { dg-final { scan-tree-dump-times "pattern recognized" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "pattern recognized" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
@@ -42,6 +42,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_mult_hi_to_si || vect_unpack } } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
-/* { dg-final { scan-tree-dump-times "pattern recognized" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "pattern recognized" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
@@ -42,6 +42,6 @@ int main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_mult_hi_to_si || vect_unpack } } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
/* { dg-final { scan-tree-dump-times "pattern recognized" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */
@@ -44,8 +44,8 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" } } */
/* When vectorizer is enhanced to vectorize accumulation into short for targets
that support accumulation into int (e.g. ia64) we'd have:
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O2 -ftree-vectorize -fno-inline -msve-vector-bits=256 -fdump-tree-vect-details" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
double mat[100][4];
double mat2[100][8];
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O2 -ftree-vectorize -msve-vector-bits=scalable" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include <stdint.h>
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O2 -ftree-vectorize -msve-vector-bits=scalable" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include <stdint.h>
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -mavx -mtune=generic -dp" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
void feat_s3_cep_dcep (int cepsize_used, float **mfc, float **feat)
{
@@ -1,5 +1,6 @@
/* { dg-options "-O3 -mavx2 -fdump-tree-vect-details" } */
/* { dg-require-effective-target avx2 } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "avx2-check.h"
#define N 32
@@ -1,5 +1,6 @@
/* { dg-do compile } */ /* PR59617 */
/* { dg-options "-O3 -mavx512f -fdump-tree-vect-details -mtune=knl" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "avx512f-gather-1.c"
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -mavx512f -mtune=knl" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
#include "avx512f-gather-4.c"
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-fopenmp-simd -O2 -mavx512f -masm=att" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* { dg-final { scan-assembler "vpadd\[^\n\r]*%xmm" } } */
/* { dg-final { scan-assembler "vpadd\[^\n\r]*%ymm" } } */
/* { dg-final { scan-assembler "vpadd\[^\n\r]*%zmm" } } */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O3 -Wno-attributes -mfpmath=sse -mfma -mtune=generic -mno-fma4" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* Test that the compiler properly optimizes floating point multiply
and add instructions into FMA3 instructions. */
@@ -1,5 +1,6 @@
/* { dg-do run } */
/* { dg-options "-O2 -ftree-vectorize -ffast-math -mavx512bw -save-temps" } */
+/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
/* { dg-require-effective-target avx512bw } */
#include "avx512bw-check.h"
@@ -11,4 +11,4 @@ Y = Y + A * X
END
! { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } }
-! { dg-final { scan-tree-dump-times "accesses have the same alignment." 1 "vect" } }
+! { dg-final { scan-tree-dump-times "accesses have the same alignment." 2 "vect" } }
Hi, In this patch I turn epilogue vectorization on by default. I had to make changes to the tests since the vectorizer dumps now show the analysis for both the first and second vectorization. This required checks like 'scan-tree-dump-times' to be raised to meet the new numbers. For some tests I simply disable the epilogue vectorization, because otherwise it makes it very difficult to test for the specific conditions the test was meant for. Bootstrapped and regression tested on aarch64 and x86_64. I am not sure whether this is the right thing to do, we might want to enable this only for certain targets and if so, I also don't know how to tackle the testing issue where all the tests that check the number of times a dump mentions something will now depend on whether that test enables epilogue vectorization or not. I was trying to avoid disabling the option for all tests, since if we do that then we aren't really testing it. Maybe we ought to enable the option for all tests, regardless of the targets default. For testing purposes. Thoughts on this? Cheers, Andre gcc/ChangeLog: 2019-08-23 Andre Vieira <andre.simoesdiasvieira@arm.com> * params.def (PARAM_VECT_EPILOGUES_NOMASK): Enable by default. gcc/testsuite/ChangeLog: 2019-08-23 Andre Vieira <andre.simoesdiasvieira@arm.com> * gcc.dg/vect/fast-math-vect-call-1.c: Raise count for tree dump scans. * gcc.dg/vect/no-fast-math-vect16.c: Likewise. * gcc.dg/vect/no-scevccp-noreassoc-slp-reduc-7.c: Likewise. * gcc.dg/vect/no-scevccp-outer-7.c: Likewise. * gcc.dg/vect/no-scevccp-vect-iv-3.c: Likewise. * gcc.dg/vect/no-section-anchors-vect-31.c: Likewise. * gcc.dg/vect/no-section-anchors-vect-64.c: Likewise. * gcc.dg/vect/no-section-anchors-vect-66.c: Likewise. * gcc.dg/vect/no-section-anchors-vect-68.c: Likewise. * gcc.dg/vect/no-vfa-vect-depend-1.c: Likewise. * gcc.dg/vect/no-vfa-vect-depend-2.c: Likewise. * gcc.dg/vect/no-vfa-vect-depend-3.c: Likewise. * gcc.dg/vect/no-vfa-vect-dv-2.c: Likewise. * gcc.dg/vect/pr33804.c: Likewise. * gcc.dg/vect/pr53773.c: Likewise. * gcc.dg/vect/pr65947-1.c: Likewise. * gcc.dg/vect/pr65947-13.c: Likewise. * gcc.dg/vect/pr65947-14.c: Likewise. * gcc.dg/vect/pr65947-4.c: Likewise. * gcc.dg/vect/pr80631-1.c: Likewise. * gcc.dg/vect/pr80631-2.c: Likewise. * gcc.dg/vect/slp-25.c: Likewise. * gcc.dg/vect/slp-reduc-2.c: Likewise. * gcc.dg/vect/slp-reduc-5.c: Likewise. * gcc.dg/vect/slp-reduc-6.c: Likewise. * gcc.dg/vect/slp-widen-mult-half.c: Likewise. * gcc.dg/vect/trapv-vect-reduc-4.c: Likewise. * gcc.dg/vect/vect-103.c: Likewise. * gcc.dg/vect/vect-109.c: Likewise. * gcc.dg/vect/vect-119.c: Likewise. * gcc.dg/vect/vect-26.c: Likewise. * gcc.dg/vect/vect-27.c: Likewise. * gcc.dg/vect/vect-29.c: Likewise. * gcc.dg/vect/vect-42.c: Likewise. * gcc.dg/vect/vect-44.c: Likewise. * gcc.dg/vect/vect-48.c: Likewise. * gcc.dg/vect/vect-50.c: Likewise. * gcc.dg/vect/vect-52.c: Likewise. * gcc.dg/vect/vect-54.c: Likewise. * gcc.dg/vect/vect-56.c: Likewise. * gcc.dg/vect/vect-58.c: Likewise. * gcc.dg/vect/vect-60.c: Likewise. * gcc.dg/vect/vect-72.c: Likewise. * gcc.dg/vect/vect-75-big-array.c: Likewise. * gcc.dg/vect/vect-75.c: Likewise. * gcc.dg/vect/vect-77-alignchecks.c: Likewise. * gcc.dg/vect/vect-77-global.c: Likewise. * gcc.dg/vect/vect-78-alignchecks.c: Likewise. * gcc.dg/vect/vect-78-global.c: Likewise. * gcc.dg/vect/vect-89-big-array.c: Likewise. * gcc.dg/vect/vect-89.c: Likewise. * gcc.dg/vect/vect-91.c: Likewise. * gcc.dg/vect/vect-92.c: Likewise. * gcc.dg/vect/vect-96.c: Likewise. * gcc.dg/vect/vect-alias-check-5.c: Likewise. * gcc.dg/vect/vect-live-2.c: Likewise. * gcc.dg/vect/vect-live-slp-1.c: Likewise. * gcc.dg/vect/vect-live-slp-3.c: Likewise. * gcc.dg/vect/vect-multitypes-1.c: Likewise. * gcc.dg/vect/vect-multitypes-3.c: Likewise. * gcc.dg/vect/vect-multitypes-4.c: Likewise. * gcc.dg/vect/vect-outer-3a-big-array.c: Likewise. * gcc.dg/vect/vect-outer-3a.c: Likewise. * gcc.dg/vect/vect-outer-4.c: Likewise. * gcc.dg/vect/vect-outer-4c-big-array.c: Likewise. * gcc.dg/vect/vect-outer-6.c: Likewise. * gcc.dg/vect/vect-peel-1.c: Likewise. * gcc.dg/vect/vect-peel-2.c: Likewise. * gcc.dg/vect/vect-peel-3.c: Likewise. * gcc.dg/vect/vect-peel-4.c: Likewise. * gcc.dg/vect/vect-reduc-6.c: Likewise. * gcc.dg/vect/vect-reduc-dot-s16a.c: Likewise. * gcc.dg/vect/vect-reduc-dot-s8a.c: Likewise. * gcc.dg/vect/vect-reduc-dot-u16b.c: Likewise. * gcc.dg/vect/vect-reduc-dot-u8a.c: Likewise. * gcc.dg/vect/vect-reduc-dot-u8b.c: Likewise. * gcc.dg/vect/vect-reduc-pattern-1a.c: Likewise. * gcc.dg/vect/vect-reduc-pattern-1b-big-array.c: Likewise. * gcc.dg/vect/vect-reduc-pattern-1c-big-array.c: Likewise. * gcc.dg/vect/vect-reduc-pattern-2a.c: Likewise. * gcc.dg/vect/vect-reduc-pattern-2b-big-array.c: Likewise. * gcc.dg/vect/vect-widen-mult-const-s16.c: Likewise. * gcc.dg/vect/vect-widen-mult-const-u16.c: Likewise. * gcc.dg/vect/vect-widen-mult-half-u8.c: Likewise. * gcc.dg/vect/vect-widen-mult-half.c: Likewise. * gcc.dg/vect/vect-widen-mult-u16.c: Likewise. * gcc.dg/vect/vect-widen-mult-u8-s16-s32.c: Likewise. * gcc.dg/vect/wrapv-vect-reduc-dot-s8b.c: Likewise. * gfortran.dg/vect/vect-4.f90: Likewise. * gcc.dg/vect/pr60092-2.c: Disable epilogue vectorization. * gcc.dg/vect/pr60092.c: Likewise. * gcc.dg/vect/slp-reduc-sad-2.c: Likewise. * gcc.dg/vect/vect-46.c: Likewise. * gcc.dg/vect/vect-86.c: Likewise. * gcc.dg/vect/vect-live-1.c: Likewise. * gcc.dg/vect/vect-live-3.c: Likewise. * gcc.dg/vect/vect-live-4.c: Likewise. * gcc.dg/vect/vect-live-slp-2.c: Likewise. * gcc.dg/vect/vect-multitypes-6.c: Likewise. * gcc.target/aarch64/sve/reduc_strict_3.c: Likewise. * gcc.target/aarch64/sve/spill_2.c: Likewise. * gcc.target/aarch64/sve/spill_6.c: Likewise. * gcc.target/i386/avx-vzeroupper-19.c: Likewise. * gcc.target/i386/avx2-vect-mask-store-move1.c: Likewise. * gcc.target/i386/avx512f-gather-2.c: Likewise. * gcc.target/i386/avx512f-gather-5.c: Likewise. * gcc.target/i386/avx512f-simd-1.c: Likewise. * gcc.target/i386/l_fma_double_1.c: Likewise. * gcc.target/i386/l_fma_double_2.c: Likewise. * gcc.target/i386/l_fma_double_3.c: Likewise. * gcc.target/i386/l_fma_double_4.c: Likewise. * gcc.target/i386/l_fma_double_5.c: Likewise. * gcc.target/i386/l_fma_double_6.c: Likewise. * gcc.target/i386/l_fma_float_1.c: Likewise. * gcc.target/i386/l_fma_float_2.c: Likewise. * gcc.target/i386/l_fma_float_3.c: Likewise. * gcc.target/i386/l_fma_float_4.c: Likewise. * gcc.target/i386/l_fma_float_5.c: Likewise. * gcc.target/i386/l_fma_float_6.c: Likewise. * gcc.target/i386/vect-perm-even-1.c: Likewise.