===================================================================
@@ -3350,6 +3350,35 @@ proc check_effective_target_aarch64_litt
}]
}
+# Return 1 if this is an AArch64 target supporting SVE.
+proc check_effective_target_aarch64_sve { } {
+ if { ![istarget aarch64*-*-*] } {
+ return 0
+ }
+ return [check_no_compiler_messages aarch64_sve assembly {
+ #if !defined (__ARM_FEATURE_SVE)
+ #error FOO
+ #endif
+ }]
+}
+
+# Return the size in bits of an SVE vector, or 0 if the size is variable.
+proc aarch64_sve_bits { } {
+ return [check_cached_effective_target aarch64_sve_bits {
+ global tool
+
+ set src dummy[pid].c
+ set f [open $src "w"]
+ puts $f "int bits = __ARM_FEATURE_SVE_BITS;"
+ close $f
+ set output [${tool}_target_compile $src "" preprocess ""]
+ file delete $src
+
+ regsub {.*bits = ([^;]*);.*} $output {\1} bits
+ expr { $bits }
+ }]
+}
+
# Return 1 if this is a compiler supporting ARC atomic operations
proc check_effective_target_arc_atomic { } {
return [check_no_compiler_messages arc_atomic assembly {
@@ -4275,6 +4304,49 @@ proc check_effective_target_arm_neon_hw
} [add_options_for_arm_neon ""]]
}
+# Return true if this is an AArch64 target that can run SVE code.
+
+proc check_effective_target_aarch64_sve_hw { } {
+ if { ![istarget aarch64*-*-*] } {
+ return 0
+ }
+ return [check_runtime aarch64_sve_hw_available {
+ int
+ main (void)
+ {
+ asm volatile ("ptrue p0.b");
+ return 0;
+ }
+ }]
+}
+
+# Return true if this is an AArch64 target that can run SVE code and
+# if its SVE vectors have exactly BITS bits.
+
+proc aarch64_sve_hw_bits { bits } {
+ if { ![check_effective_target_aarch64_sve_hw] } {
+ return 0
+ }
+ return [check_runtime aarch64_sve${bits}_hw [subst {
+ int
+ main (void)
+ {
+ int res;
+ asm volatile ("cntd %0" : "=r" (res));
+ if (res * 64 != $bits)
+ __builtin_abort ();
+ return 0;
+ }
+ }]]
+}
+
+# Return true if this is an AArch64 target that can run SVE code and
+# if its SVE vectors have exactly 256 bits.
+
+proc check_effective_target_aarch64_sve256_hw { } {
+ return [aarch64_sve_hw_bits 256]
+}
+
proc check_effective_target_arm_neonv2_hw { } {
return [check_runtime arm_neon_hwv2_available {
#include "arm_neon.h"
@@ -5531,7 +5603,8 @@ proc check_effective_target_vect_perm {
} else {
set et_vect_perm_saved($et_index) 0
if { [is-effective-target arm_neon]
- || [istarget aarch64*-*-*]
+ || ([istarget aarch64*-*-*]
+ && ![check_effective_target_vect_variable_length])
|| [istarget powerpc*-*-*]
|| [istarget spu-*-*]
|| [istarget i?86-*-*] || [istarget x86_64-*-*]
@@ -5636,7 +5709,8 @@ proc check_effective_target_vect_perm_by
if { ([is-effective-target arm_neon]
&& [is-effective-target arm_little_endian])
|| ([istarget aarch64*-*-*]
- && [is-effective-target aarch64_little_endian])
+ && [is-effective-target aarch64_little_endian]
+ && ![check_effective_target_vect_variable_length])
|| [istarget powerpc*-*-*]
|| [istarget spu-*-*]
|| ([istarget mips-*.*]
@@ -5675,7 +5749,8 @@ proc check_effective_target_vect_perm_sh
if { ([is-effective-target arm_neon]
&& [is-effective-target arm_little_endian])
|| ([istarget aarch64*-*-*]
- && [is-effective-target aarch64_little_endian])
+ && [is-effective-target aarch64_little_endian]
+ && ![check_effective_target_vect_variable_length])
|| [istarget powerpc*-*-*]
|| [istarget spu-*-*]
|| ([istarget mips*-*-*]
@@ -5735,7 +5810,8 @@ proc check_effective_target_vect_widen_s
} else {
set et_vect_widen_sum_hi_to_si_pattern_saved($et_index) 0
if { [istarget powerpc*-*-*]
- || [istarget aarch64*-*-*]
+ || ([istarget aarch64*-*-*]
+ && ![check_effective_target_aarch64_sve])
|| [is-effective-target arm_neon]
|| [istarget ia64-*-*] } {
set et_vect_widen_sum_hi_to_si_pattern_saved($et_index) 1
@@ -5847,7 +5923,8 @@ proc check_effective_target_vect_widen_m
set et_vect_widen_mult_qi_to_hi_saved($et_index) 0
}
if { [istarget powerpc*-*-*]
- || [istarget aarch64*-*-*]
+ || ([istarget aarch64*-*-*]
+ && ![check_effective_target_aarch64_sve])
|| [is-effective-target arm_neon]
|| ([istarget s390*-*-*]
&& [check_effective_target_s390_vx]) } {
@@ -5885,7 +5962,8 @@ proc check_effective_target_vect_widen_m
if { [istarget powerpc*-*-*]
|| [istarget spu-*-*]
|| [istarget ia64-*-*]
- || [istarget aarch64*-*-*]
+ || ([istarget aarch64*-*-*]
+ && ![check_effective_target_aarch64_sve])
|| [istarget i?86-*-*] || [istarget x86_64-*-*]
|| [is-effective-target arm_neon]
|| ([istarget s390*-*-*]
@@ -6347,12 +6425,16 @@ proc check_effective_target_vect_natural
# alignment during vectorization.
proc check_effective_target_vect_element_align_preferred { } {
- return [check_effective_target_vect_variable_length]
+ return [expr { [check_effective_target_aarch64_sve]
+ && [check_effective_target_vect_variable_length] }]
}
# Return 1 if we can align stack data to the preferred vector alignment.
proc check_effective_target_vect_align_stack_vars { } {
+ if { [check_effective_target_aarch64_sve] } {
+ return [check_effective_target_vect_variable_length]
+ }
return 1
}
@@ -6424,7 +6506,8 @@ proc check_effective_target_vect_load_la
} else {
set et_vect_load_lanes 0
if { ([istarget arm*-*-*] && [check_effective_target_arm_neon_ok])
- || [istarget aarch64*-*-*] } {
+ || ([istarget aarch64*-*-*]
+ && ![check_effective_target_aarch64_sve]) } {
set et_vect_load_lanes 1
}
}
@@ -6436,7 +6519,7 @@ proc check_effective_target_vect_load_la
# Return 1 if the target supports vector masked stores.
proc check_effective_target_vect_masked_store { } {
- return 0
+ return [check_effective_target_aarch64_sve]
}
# Return 1 if the target supports vector conditional operations, 0 otherwise.
@@ -6704,6 +6787,9 @@ foreach N {2 3 4 8} {
proc available_vector_sizes { } {
set result {}
if { [istarget aarch64*-*-*] } {
+ if { [check_effective_target_aarch64_sve] } {
+ lappend result [aarch64_sve_bits]
+ }
lappend result 128 64
} elseif { [istarget arm*-*-*]
&& [check_effective_target_arm_neon_ok] } {
===================================================================
@@ -76,4 +76,12 @@ check_vect (void)
signal (SIGILL, SIG_DFL);
}
-#define VECTOR_BITS 128
+#if defined (__ARM_FEATURE_SVE)
+# if __ARM_FEATURE_SVE_BITS == 0
+# define VECTOR_BITS 1024
+# else
+# define VECTOR_BITS __ARM_FEATURE_SVE_BITS
+# endif
+#else
+# define VECTOR_BITS 128
+#endif
===================================================================
@@ -25,4 +25,4 @@ foo ()
but the loop reads only one element at a time, and DOM cannot resolve these.
The same happens on powerpc depending on the SIMD support available. */
-/* { dg-final { scan-tree-dump "return 28;" "optimized" { xfail { { alpha*-*-* hppa*64*-*-* } || { lp64 && { powerpc*-*-* sparc*-*-* riscv*-*-* } } } } } } */
+/* { dg-final { scan-tree-dump "return 28;" "optimized" { xfail { { alpha*-*-* hppa*64*-*-* } || { { lp64 && { powerpc*-*-* sparc*-*-* riscv*-*-* } } || aarch64_sve } } } } } */
===================================================================
@@ -17,4 +17,6 @@ void foo(unsigned *p1, unsigned short *p
p1[n] = p2[n * 2];
}
-/* { dg-final { scan-tree-dump "BB vectorization with gaps at the end of a load is not supported" "slp1" } } */
+/* Disable for SVE because for long or variable-length vectors we don't
+ get an unrolled epilogue loop. */
+/* { dg-final { scan-tree-dump "BB vectorization with gaps at the end of a load is not supported" "slp1" { target { ! aarch64_sve } } } } */
===================================================================
@@ -51,4 +51,7 @@ 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" } } */
+/* Requires reverse for variable-length SVE, which is implemented for
+ by a later patch. Until then we report it twice, once for SVE and
+ once for 128-bit Advanced SIMD. */
+/* { dg-final { scan-tree-dump-times "dependence distance negative" 1 "vect" { xfail { aarch64_sve && vect_variable_length } } } } */
===================================================================
@@ -183,4 +183,7 @@ 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" } } */
+/* f4 requires reverse for SVE, which is implemented by a later patch.
+ Until then we report it twice, once for SVE and once for 128-bit
+ Advanced SIMD. */
+/* { dg-final { scan-tree-dump-times "dependence distance negative" 4 "vect" { xfail { aarch64_sve && vect_variable_length } } } } */
===================================================================
@@ -107,6 +107,8 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { target { vect_strided8 && { ! { vect_no_align} } } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { ! { vect_strided8 || vect_no_align } } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target { ! vect_perm } } } } */
+/* We fail to vectorize the second loop with variable-length SVE but
+ fall back to 128-bit vectors, which does use SLP. */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target { ! vect_perm } xfail aarch64_sve } } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target vect_perm } } } */
===================================================================
@@ -57,4 +57,6 @@ 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 } } } } } */
+/* Needs store_lanes for SVE, otherwise falls back to Advanced SIMD.
+ Will be fixed when SVE LOAD_LANES support is added. */
+/* { dg-final { scan-tree-dump-times "Alignment of access forced using peeling" 2 "vect" { xfail { { { ! vect_unaligned_possible } || { ! vect_natural_alignment } } && { ! { aarch64_sve && vect_variable_length } } } } } } */
===================================================================
@@ -104,7 +104,9 @@ int main (int argc, const char* argv[])
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_perm } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target { vect_perm3_int && {! vect_load_lanes } } } } } */
+/* Fails for variable-length SVE because we fall back to Advanced SIMD
+ and use LD3/ST3. Will be fixed when SVE LOAD_LANES support is added. */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target { vect_perm3_int && {! vect_load_lanes } } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 0 "vect" { target vect_load_lanes } } } */
/* { dg-final { scan-tree-dump "note: Built SLP cancelled: can use load/store-lanes" "vect" { target { vect_perm3_int && vect_load_lanes } } } } */
/* { dg-final { scan-tree-dump "LOAD_LANES" "vect" { target vect_load_lanes } } } */
===================================================================
@@ -103,7 +103,9 @@ int main (int argc, const char* argv[])
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_perm } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target { vect_perm3_int && {! vect_load_lanes } } } } } */
+/* Fails for variable-length SVE because we fall back to Advanced SIMD
+ and use LD3/ST3. Will be fixed when SVE LOAD_LANES support is added. */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target { vect_perm3_int && {! vect_load_lanes } } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target vect_load_lanes } } } */
/* { dg-final { scan-tree-dump "note: Built SLP cancelled: can use load/store-lanes" "vect" { target { vect_perm3_int && vect_load_lanes } } } } */
/* { dg-final { scan-tree-dump "LOAD_LANES" "vect" { target vect_load_lanes } } } */
===================================================================
@@ -57,10 +57,11 @@ int main (int argc, const char* argv[])
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 2 "vect" { target { ! { vect_perm_short || vect_load_lanes } } } } } */
+/* Fails for variable-length SVE because we fall back to Advanced SIMD
+ and use LD3/ST3. Will be fixed when SVE LOAD_LANES support is added. */
+/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 2 "vect" { target { ! { vect_perm_short || vect_load_lanes } } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_perm_short || vect_load_lanes } } } } */
/* { dg-final { scan-tree-dump-times "permutation requires at least three vectors" 1 "vect" { target { vect_perm_short && { ! vect_perm3_short } } } } } */
/* { dg-final { scan-tree-dump-not "permutation requires at least three vectors" "vect" { target vect_perm3_short } } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 0 "vect" { target { { ! vect_perm3_short } || vect_load_lanes } } } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target { vect_perm3_short && { ! vect_load_lanes } } } } } */
-
===================================================================
@@ -58,4 +58,7 @@ int main (void)
/* The initialization loop in main also gets vectorized. */
/* { dg-final { scan-tree-dump-times "vect_recog_dot_prod_pattern: detected" 1 "vect" { xfail *-*-* } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target { vect_short_mult && { vect_widen_sum_hi_to_si && vect_unpack } } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_widen_sum_hi_to_si_pattern || { ! vect_unpack } } } } } */
+/* We can't yet create the necessary SLP constant vector for variable-length
+ SVE and so fall back to Advanced SIMD. This means that we repeat each
+ analysis note. */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_widen_sum_hi_to_si_pattern || { { ! vect_unpack } || { aarch64_sve && vect_variable_length } } } } } } */
===================================================================
@@ -34,6 +34,9 @@ int main (void)
return main1 ();
}
-/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" { target { ! { vect_perm } } } } } */
+/* Requires reverse for SVE, which is implemented by a later patch.
+ Until then we fall back to Advanced SIMD and successfully vectorize
+ the loop. */
+/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" { target { ! vect_perm } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_perm } } } */
===================================================================
@@ -25,4 +25,7 @@ unsigned int foo (const unsigned int x[O
return sum;
}
-/* { dg-final { scan-tree-dump-times "Detected interleaving load of size 2" 1 "vect" } } */
+/* Requires load-lanes for SVE, which is implemented by a later patch.
+ Until then we report it twice, once for SVE and once for 128-bit
+ Advanced SIMD. */
+/* { dg-final { scan-tree-dump-times "Detected interleaving load of size 2" 1 "vect" { xfail { aarch64_sve && vect_variable_length } } } } */
===================================================================
@@ -83,4 +83,6 @@ main (void)
}
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { ! vect_masked_store } xfail { { vect_no_align && { ! vect_hw_misalign } } || { ! vect_strided2 } } } } } */
-/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { target { vect_masked_store } } } } */
+/* Fails for variable-length SVE because we can't yet handle the
+ interleaved load. This is fixed by a later patch. */
+/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" { target vect_masked_store xfail { aarch64_sve && vect_variable_length } } } } */
===================================================================
@@ -69,4 +69,7 @@ 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" } } */
+/* We can't yet create the necessary SLP constant vector for variable-length
+ SVE and so fall back to Advanced SIMD. This means that we repeat each
+ analysis note. */
+/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 4 "vect" { xfail { aarch64_sve && vect_variable_length } } } }*/
===================================================================
@@ -63,4 +63,7 @@ main (void)
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" } } */
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" } } */
-/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 2 "vect" } } */
+/* We can't yet create the necessary SLP constant vector for variable-length
+ SVE and so fall back to Advanced SIMD. This means that we repeat each
+ analysis note. */
+/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 2 "vect" { xfail { aarch64_sve && vect_variable_length } } } } */
===================================================================
@@ -70,4 +70,7 @@ 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" } } */
+/* We can't yet create the necessary SLP constant vector for variable-length
+ SVE and so fall back to Advanced SIMD. This means that we repeat each
+ analysis note. */
+/* { dg-final { scan-tree-dump-times "vec_stmt_relevant_p: stmt live but not relevant" 4 "vect" { xfail { aarch64_sve && vect_variable_length } } } } */
===================================================================
@@ -37,5 +37,5 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_mult_pattern: detected" 2 "vect" { target aarch64*-*-* } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_mult_pattern: detected" 2 "vect" { target aarch64*-*-* xfail aarch64_sve } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target aarch64*-*-* } } } */
===================================================================
@@ -36,5 +36,5 @@ main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_mult_pattern: detected" 2 "vect" { target aarch64*-*-* } } } */
+/* { dg-final { scan-tree-dump-times "vect_recog_mult_pattern: detected" 2 "vect" { target aarch64*-*-* xfail aarch64_sve } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target aarch64*-*-* } } } */
===================================================================
@@ -59,6 +59,8 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vect_recog_widen_shift_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { ! vect_widen_shift } } } } */
+/* Requires LD4 for variable-length SVE. Until that's supported we fall
+ back to Advanced SIMD, which does have widening shifts. */
+/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { ! vect_widen_shift } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
===================================================================
@@ -63,7 +63,9 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vect_recog_widen_shift_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { { ! vect_sizes_32B_16B } && { ! vect_widen_shift } } } } } */
+/* Requires LD4 for variable-length SVE. Until that's supported we fall
+ back to Advanced SIMD, which does have widening shifts. */
+/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { { ! vect_sizes_32B_16B } && { ! vect_widen_shift } } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 8 "vect" { target vect_sizes_32B_16B } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
===================================================================
@@ -59,7 +59,9 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 2 "vect" { target { ! vect_widen_shift } } } } */
+/* Requires LD4 for variable-length SVE. Until that's supported we fall
+ back to Advanced SIMD, which does have widening shifts. */
+/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 2 "vect" { target { ! vect_widen_shift } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 1 "vect" { target vect_widen_shift } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
===================================================================
@@ -63,6 +63,8 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vect_recog_widen_shift_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { ! vect_widen_shift } } } } */
+/* Requires LD4 for variable-length SVE. Until that's supported we fall
+ back to Advanced SIMD, which does have widening shifts. */
+/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { ! vect_widen_shift } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
===================================================================
@@ -67,7 +67,9 @@ int main (void)
/* { dg-final { scan-tree-dump-times "vect_recog_widen_shift_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 2 "vect" { target vect_widen_shift } } } */
-/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { { ! vect_sizes_32B_16B } && { ! vect_widen_shift } } } } } */
+/* Requires LD4 for variable-length SVE. Until that's supported we fall
+ back to Advanced SIMD, which does have widening shifts. */
+/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 4 "vect" { target { { ! vect_sizes_32B_16B } && { ! vect_widen_shift } } xfail { aarch64_sve && vect_variable_length } } } } */
/* { dg-final { scan-tree-dump-times "vect_recog_over_widening_pattern: detected" 8 "vect" { target vect_sizes_32B_16B } } } */
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */