Harald Anlauf b1bee29167 PR libfortran/99218 - matmul on temporary array accesses invalid memory ... Do not invoke tuned rank-2 times rank-2 matmul if rank(b) == 1. libgfortran/ChangeLog: PR libfortran/99218 * m4/matmul_internal.m4: Invoke tuned matmul only for rank(b)>1. * generated/matmul_c10.c: Regenerated. * generated/matmul_c16.c: Likewise. * generated/matmul_c4.c: Likewise. * generated/matmul_c8.c: Likewise. * generated/matmul_i1.c: Likewise. * generated/matmul_i16.c: Likewise. * generated/matmul_i2.c: Likewise. * generated/matmul_i4.c: Likewise. * generated/matmul_i8.c: Likewise. * generated/matmul_r10.c: Likewise. * generated/matmul_r16.c: Likewise. * generated/matmul_r4.c: Likewise. * generated/matmul_r8.c: Likewise. * generated/matmulavx128_c10.c: Likewise. * generated/matmulavx128_c16.c: Likewise. * generated/matmulavx128_c4.c: Likewise. * generated/matmulavx128_c8.c: Likewise. * generated/matmulavx128_i1.c: Likewise. * generated/matmulavx128_i16.c: Likewise. * generated/matmulavx128_i2.c: Likewise. * generated/matmulavx128_i4.c: Likewise. * generated/matmulavx128_i8.c: Likewise. * generated/matmulavx128_r10.c: Likewise. * generated/matmulavx128_r16.c: Likewise. * generated/matmulavx128_r4.c: Likewise. * generated/matmulavx128_r8.c: Likewise. gcc/testsuite/ChangeLog: PR libfortran/99218 * gfortran.dg/matmul_21.f90: New test.		2021-03-05 20:58:51 +01:00
..
_abs_c4.F90
_abs_c8.F90
_abs_c10.F90
_abs_c16.F90
_abs_i4.F90
_abs_i8.F90
_abs_i16.F90
_abs_r4.F90
_abs_r8.F90
_abs_r10.F90
_abs_r16.F90
_acos_r4.F90
_acos_r8.F90
_acos_r10.F90
_acos_r16.F90
_acosh_r4.F90
_acosh_r8.F90
_acosh_r10.F90
_acosh_r16.F90
_aimag_c4.F90
_aimag_c8.F90
_aimag_c10.F90
_aimag_c16.F90
_aint_r4.F90
_aint_r8.F90
_aint_r10.F90
_aint_r16.F90
_anint_r4.F90
_anint_r8.F90
_anint_r10.F90
_anint_r16.F90
_asin_r4.F90
_asin_r8.F90
_asin_r10.F90
_asin_r16.F90
_asinh_r4.F90
_asinh_r8.F90
_asinh_r10.F90
_asinh_r16.F90
_atan2_r4.F90
_atan2_r8.F90
_atan2_r10.F90
_atan2_r16.F90
_atan_r4.F90
_atan_r8.F90
_atan_r10.F90
_atan_r16.F90
_atanh_r4.F90
_atanh_r8.F90
_atanh_r10.F90
_atanh_r16.F90
_conjg_c4.F90
_conjg_c8.F90
_conjg_c10.F90
_conjg_c16.F90
_cos_c4.F90
_cos_c8.F90
_cos_c10.F90
_cos_c16.F90
_cos_r4.F90
_cos_r8.F90
_cos_r10.F90
_cos_r16.F90
_cosh_r4.F90
_cosh_r8.F90
_cosh_r10.F90
_cosh_r16.F90
_dim_i4.F90
_dim_i8.F90
_dim_i16.F90
_dim_r4.F90
_dim_r8.F90
_dim_r10.F90
_dim_r16.F90
_exp_c4.F90
_exp_c8.F90
_exp_c10.F90
_exp_c16.F90
_exp_r4.F90
_exp_r8.F90
_exp_r10.F90
_exp_r16.F90
_log10_r4.F90
_log10_r8.F90
_log10_r10.F90
_log10_r16.F90
_log_c4.F90
_log_c8.F90
_log_c10.F90
_log_c16.F90
_log_r4.F90
_log_r8.F90
_log_r10.F90
_log_r16.F90
_mod_i4.F90
_mod_i8.F90
_mod_i16.F90
_mod_r4.F90
_mod_r8.F90
_mod_r10.F90
_mod_r16.F90
_sign_i4.F90
_sign_i8.F90
_sign_i16.F90
_sign_r4.F90
_sign_r8.F90
_sign_r10.F90
_sign_r16.F90
_sin_c4.F90
_sin_c8.F90
_sin_c10.F90
_sin_c16.F90
_sin_r4.F90
_sin_r8.F90
_sin_r10.F90
_sin_r16.F90
_sinh_r4.F90
_sinh_r8.F90
_sinh_r10.F90
_sinh_r16.F90
_sqrt_c4.F90
_sqrt_c8.F90
_sqrt_c10.F90
_sqrt_c16.F90
_sqrt_r4.F90
_sqrt_r8.F90
_sqrt_r10.F90
_sqrt_r16.F90
_tan_r4.F90
_tan_r8.F90
_tan_r10.F90
_tan_r16.F90
_tanh_r4.F90
_tanh_r8.F90
_tanh_r10.F90
_tanh_r16.F90
all_l1.c
all_l2.c
all_l4.c
all_l8.c
all_l16.c
any_l1.c
any_l2.c
any_l4.c
any_l8.c
any_l16.c
bessel_r4.c
bessel_r8.c
bessel_r10.c
bessel_r16.c
count_1_l.c
count_2_l.c
count_4_l.c
count_8_l.c
count_16_l.c
cshift0_c4.c
cshift0_c8.c
cshift0_c10.c
cshift0_c16.c
cshift0_i1.c
cshift0_i2.c
cshift0_i4.c
cshift0_i8.c
cshift0_i16.c
cshift0_r4.c
cshift0_r8.c
cshift0_r10.c
cshift0_r16.c
cshift1_4_c4.c
cshift1_4_c8.c
cshift1_4_c10.c
cshift1_4_c16.c
cshift1_4_i1.c
cshift1_4_i2.c
cshift1_4_i4.c
cshift1_4_i8.c
cshift1_4_i16.c
cshift1_4_r4.c
cshift1_4_r8.c
cshift1_4_r10.c
cshift1_4_r16.c
cshift1_4.c
cshift1_8_c4.c
cshift1_8_c8.c
cshift1_8_c10.c
cshift1_8_c16.c
cshift1_8_i1.c
cshift1_8_i2.c
cshift1_8_i4.c
cshift1_8_i8.c
cshift1_8_i16.c
cshift1_8_r4.c
cshift1_8_r8.c
cshift1_8_r10.c
cshift1_8_r16.c
cshift1_8.c
cshift1_16_c4.c
cshift1_16_c8.c
cshift1_16_c10.c
cshift1_16_c16.c
cshift1_16_i1.c
cshift1_16_i2.c
cshift1_16_i4.c
cshift1_16_i8.c
cshift1_16_i16.c
cshift1_16_r4.c
cshift1_16_r8.c
cshift1_16_r10.c
cshift1_16_r16.c
cshift1_16.c
eoshift1_4.c
eoshift1_8.c
eoshift1_16.c
eoshift3_4.c
eoshift3_8.c
eoshift3_16.c
findloc0_c4.c
findloc0_c8.c
findloc0_c10.c
findloc0_c16.c
findloc0_i1.c
findloc0_i2.c
findloc0_i4.c
findloc0_i8.c
findloc0_i16.c
findloc0_r4.c
findloc0_r8.c
findloc0_r10.c
findloc0_r16.c
findloc0_s1.c
findloc0_s4.c
findloc1_c4.c
findloc1_c8.c
findloc1_c10.c
findloc1_c16.c
findloc1_i1.c
findloc1_i2.c
findloc1_i4.c
findloc1_i8.c
findloc1_i16.c
findloc1_r4.c
findloc1_r8.c
findloc1_r10.c
findloc1_r16.c
findloc1_s1.c
findloc1_s4.c
findloc2_s1.c
findloc2_s4.c
iall_i1.c
iall_i2.c
iall_i4.c
iall_i8.c
iall_i16.c
iany_i1.c
iany_i2.c
iany_i4.c
iany_i8.c
iany_i16.c
in_pack_c4.c
in_pack_c8.c
in_pack_c10.c
in_pack_c16.c
in_pack_i1.c
in_pack_i2.c
in_pack_i4.c
in_pack_i8.c
in_pack_i16.c
in_pack_r4.c
in_pack_r8.c
in_pack_r10.c
in_pack_r16.c
in_unpack_c4.c
in_unpack_c8.c
in_unpack_c10.c
in_unpack_c16.c
in_unpack_i1.c
in_unpack_i2.c
in_unpack_i4.c
in_unpack_i8.c
in_unpack_i16.c
in_unpack_r4.c
in_unpack_r8.c
in_unpack_r10.c
in_unpack_r16.c
iparity_i1.c
iparity_i2.c
iparity_i4.c
iparity_i8.c
iparity_i16.c
matmul_c4.c
matmul_c8.c
matmul_c10.c
matmul_c16.c
matmul_i1.c
matmul_i2.c
matmul_i4.c
matmul_i8.c
matmul_i16.c
matmul_l4.c
matmul_l8.c
matmul_l16.c
matmul_r4.c
matmul_r8.c
matmul_r10.c
matmul_r16.c
matmulavx128_c4.c
matmulavx128_c8.c
matmulavx128_c10.c
matmulavx128_c16.c
matmulavx128_i1.c
matmulavx128_i2.c
matmulavx128_i4.c
matmulavx128_i8.c
matmulavx128_i16.c
matmulavx128_r4.c
matmulavx128_r8.c
matmulavx128_r10.c
matmulavx128_r16.c
maxloc0_4_i1.c
maxloc0_4_i2.c
maxloc0_4_i4.c
maxloc0_4_i8.c
maxloc0_4_i16.c
maxloc0_4_r4.c
maxloc0_4_r8.c
maxloc0_4_r10.c
maxloc0_4_r16.c
maxloc0_4_s1.c
maxloc0_4_s4.c
maxloc0_8_i1.c
maxloc0_8_i2.c
maxloc0_8_i4.c
maxloc0_8_i8.c
maxloc0_8_i16.c
maxloc0_8_r4.c
maxloc0_8_r8.c
maxloc0_8_r10.c
maxloc0_8_r16.c
maxloc0_8_s1.c
maxloc0_8_s4.c
maxloc0_16_i1.c
maxloc0_16_i2.c
maxloc0_16_i4.c
maxloc0_16_i8.c
maxloc0_16_i16.c
maxloc0_16_r4.c
maxloc0_16_r8.c
maxloc0_16_r10.c
maxloc0_16_r16.c
maxloc0_16_s1.c
maxloc0_16_s4.c
maxloc1_4_i1.c
maxloc1_4_i2.c
maxloc1_4_i4.c
maxloc1_4_i8.c
maxloc1_4_i16.c
maxloc1_4_r4.c
maxloc1_4_r8.c
maxloc1_4_r10.c
maxloc1_4_r16.c
maxloc1_4_s1.c
maxloc1_4_s4.c
maxloc1_8_i1.c
maxloc1_8_i2.c
maxloc1_8_i4.c
maxloc1_8_i8.c
maxloc1_8_i16.c
maxloc1_8_r4.c
maxloc1_8_r8.c
maxloc1_8_r10.c
maxloc1_8_r16.c
maxloc1_8_s1.c
maxloc1_8_s4.c
maxloc1_16_i1.c
maxloc1_16_i2.c
maxloc1_16_i4.c
maxloc1_16_i8.c
maxloc1_16_i16.c
maxloc1_16_r4.c
maxloc1_16_r8.c
maxloc1_16_r10.c
maxloc1_16_r16.c
maxloc1_16_s1.c
maxloc1_16_s4.c
maxloc2_4_s1.c
maxloc2_4_s4.c
maxloc2_8_s1.c
maxloc2_8_s4.c
maxloc2_16_s1.c
maxloc2_16_s4.c
maxval0_s1.c
maxval0_s4.c
maxval1_s1.c
maxval1_s4.c
maxval_i1.c
maxval_i2.c
maxval_i4.c
maxval_i8.c
maxval_i16.c
maxval_r4.c
maxval_r8.c
maxval_r10.c
maxval_r16.c
minloc0_4_i1.c
minloc0_4_i2.c
minloc0_4_i4.c
minloc0_4_i8.c
minloc0_4_i16.c
minloc0_4_r4.c
minloc0_4_r8.c
minloc0_4_r10.c
minloc0_4_r16.c
minloc0_4_s1.c
minloc0_4_s4.c
minloc0_8_i1.c
minloc0_8_i2.c
minloc0_8_i4.c
minloc0_8_i8.c
minloc0_8_i16.c
minloc0_8_r4.c
minloc0_8_r8.c
minloc0_8_r10.c
minloc0_8_r16.c
minloc0_8_s1.c
minloc0_8_s4.c
minloc0_16_i1.c
minloc0_16_i2.c
minloc0_16_i4.c
minloc0_16_i8.c
minloc0_16_i16.c
minloc0_16_r4.c
minloc0_16_r8.c
minloc0_16_r10.c
minloc0_16_r16.c
minloc0_16_s1.c
minloc0_16_s4.c
minloc1_4_i1.c
minloc1_4_i2.c
minloc1_4_i4.c
minloc1_4_i8.c
minloc1_4_i16.c
minloc1_4_r4.c
minloc1_4_r8.c
minloc1_4_r10.c
minloc1_4_r16.c
minloc1_4_s1.c
minloc1_4_s4.c
minloc1_8_i1.c
minloc1_8_i2.c
minloc1_8_i4.c
minloc1_8_i8.c
minloc1_8_i16.c
minloc1_8_r4.c
minloc1_8_r8.c
minloc1_8_r10.c
minloc1_8_r16.c
minloc1_8_s1.c
minloc1_8_s4.c
minloc1_16_i1.c
minloc1_16_i2.c
minloc1_16_i4.c
minloc1_16_i8.c
minloc1_16_i16.c
minloc1_16_r4.c
minloc1_16_r8.c
minloc1_16_r10.c
minloc1_16_r16.c
minloc1_16_s1.c
minloc1_16_s4.c
minloc2_4_s1.c
minloc2_4_s4.c
minloc2_8_s1.c
minloc2_8_s4.c
minloc2_16_s1.c
minloc2_16_s4.c
minval0_s1.c
minval0_s4.c
minval1_s1.c
minval1_s4.c
minval_i1.c
minval_i2.c
minval_i4.c
minval_i8.c
minval_i16.c
minval_r4.c
minval_r8.c
minval_r10.c
minval_r16.c
misc_specifics.F90
norm2_r4.c
norm2_r8.c
norm2_r10.c
norm2_r16.c
pack_c4.c
pack_c8.c
pack_c10.c
pack_c16.c
pack_i1.c
pack_i2.c
pack_i4.c
pack_i8.c
pack_i16.c
pack_r4.c
pack_r8.c
pack_r10.c
pack_r16.c
parity_l1.c
parity_l2.c
parity_l4.c
parity_l8.c
parity_l16.c
pow_c4_i4.c
pow_c4_i8.c
pow_c4_i16.c
pow_c8_i4.c
pow_c8_i8.c
pow_c8_i16.c
pow_c10_i4.c
pow_c10_i8.c
pow_c10_i16.c
pow_c16_i4.c
pow_c16_i8.c
pow_c16_i16.c
pow_i4_i4.c
pow_i4_i8.c
pow_i4_i16.c
pow_i8_i4.c
pow_i8_i8.c
pow_i8_i16.c
pow_i16_i4.c
pow_i16_i8.c
pow_i16_i16.c
pow_r4_i8.c
pow_r4_i16.c
pow_r8_i8.c
pow_r8_i16.c
pow_r10_i8.c
pow_r10_i16.c
pow_r16_i4.c
pow_r16_i8.c
pow_r16_i16.c
product_c4.c
product_c8.c
product_c10.c
product_c16.c
product_i1.c
product_i2.c
product_i4.c
product_i8.c
product_i16.c
product_r4.c
product_r8.c
product_r10.c
product_r16.c
reshape_c4.c
reshape_c8.c
reshape_c10.c
reshape_c16.c
reshape_i4.c
reshape_i8.c
reshape_i16.c
reshape_r4.c
reshape_r8.c
reshape_r10.c
reshape_r16.c
shape_i1.c
shape_i2.c
shape_i4.c
shape_i8.c
shape_i16.c
spread_c4.c
spread_c8.c
spread_c10.c
spread_c16.c
spread_i1.c
spread_i2.c
spread_i4.c
spread_i8.c
spread_i16.c
spread_r4.c
spread_r8.c
spread_r10.c
spread_r16.c
sum_c4.c
sum_c8.c
sum_c10.c
sum_c16.c
sum_i1.c
sum_i2.c
sum_i4.c
sum_i8.c
sum_i16.c
sum_r4.c
sum_r8.c
sum_r10.c
sum_r16.c
unpack_c4.c
unpack_c8.c
unpack_c10.c
unpack_c16.c
unpack_i1.c
unpack_i2.c
unpack_i4.c
unpack_i8.c
unpack_i16.c
unpack_r4.c
unpack_r8.c
unpack_r10.c
unpack_r16.c