From 4f4fabd73312efba10f80f132d2ce59a292ddd97 Mon Sep 17 00:00:00 2001 From: Thomas Koenig Date: Sat, 25 Aug 2018 21:31:30 +0000 Subject: re PR fortran/86704 (Segmentation fault when using matmul in combination with transpose) 2018-08-25 Thomas Koenig PR libfortran/86704 * m4/matmul_internal.m4: Correct calculation of needed buffer size for arrays of shape (1,n). * generated/matmul_c10.c: Regenerated * generated/matmul_c16.c: Regenerated * generated/matmul_c4.c: Regenerated * generated/matmul_c8.c: Regenerated * generated/matmul_i1.c: Regenerated * generated/matmul_i16.c: Regenerated * generated/matmul_i2.c: Regenerated * generated/matmul_i4.c: Regenerated * generated/matmul_i8.c: Regenerated * generated/matmul_r10.c: Regenerated * generated/matmul_r16.c: Regenerated * generated/matmul_r4.c: Regenerated * generated/matmul_r8.c: Regenerated * generated/matmulavx128_c10.c: Regenerated * generated/matmulavx128_c16.c: Regenerated * generated/matmulavx128_c4.c: Regenerated * generated/matmulavx128_c8.c: Regenerated * generated/matmulavx128_i1.c: Regenerated * generated/matmulavx128_i16.c: Regenerated * generated/matmulavx128_i2.c: Regenerated * generated/matmulavx128_i4.c: Regenerated * generated/matmulavx128_i8.c: Regenerated * generated/matmulavx128_r10.c: Regenerated * generated/matmulavx128_r16.c: Regenerated * generated/matmulavx128_r4.c: Regenerated * generated/matmulavx128_r8.c: Regenerated 2018-08-25 Thomas Koenig PR libfortran/86704 * gfortran.dg/matmul_19.f90: New test. From-SVN: r263856 --- libgfortran/generated/matmul_i2.c | 45 ++++++++++++++++++++++++++++++--------- 1 file changed, 35 insertions(+), 10 deletions(-) (limited to 'libgfortran/generated/matmul_i2.c') diff --git a/libgfortran/generated/matmul_i2.c b/libgfortran/generated/matmul_i2.c index ae8a459..e4246e9 100644 --- a/libgfortran/generated/matmul_i2.c +++ b/libgfortran/generated/matmul_i2.c @@ -317,8 +317,13 @@ matmul_i2_avx (gfc_array_i2 * const restrict retarray, return; /* Adjust size of t1 to what is needed. */ - index_type t1_dim; - t1_dim = (a_dim1 - (ycount > 1)) * 256 + b_dim1; + index_type t1_dim, a_sz; + if (aystride == 1) + a_sz = rystride; + else + a_sz = a_dim1; + + t1_dim = a_sz * 256 + b_dim1; if (t1_dim > 65536) t1_dim = 65536; @@ -869,8 +874,13 @@ matmul_i2_avx2 (gfc_array_i2 * const restrict retarray, return; /* Adjust size of t1 to what is needed. */ - index_type t1_dim; - t1_dim = (a_dim1 - (ycount > 1)) * 256 + b_dim1; + index_type t1_dim, a_sz; + if (aystride == 1) + a_sz = rystride; + else + a_sz = a_dim1; + + t1_dim = a_sz * 256 + b_dim1; if (t1_dim > 65536) t1_dim = 65536; @@ -1421,8 +1431,13 @@ matmul_i2_avx512f (gfc_array_i2 * const restrict retarray, return; /* Adjust size of t1 to what is needed. */ - index_type t1_dim; - t1_dim = (a_dim1 - (ycount > 1)) * 256 + b_dim1; + index_type t1_dim, a_sz; + if (aystride == 1) + a_sz = rystride; + else + a_sz = a_dim1; + + t1_dim = a_sz * 256 + b_dim1; if (t1_dim > 65536) t1_dim = 65536; @@ -1987,8 +2002,13 @@ matmul_i2_vanilla (gfc_array_i2 * const restrict retarray, return; /* Adjust size of t1 to what is needed. */ - index_type t1_dim; - t1_dim = (a_dim1 - (ycount > 1)) * 256 + b_dim1; + index_type t1_dim, a_sz; + if (aystride == 1) + a_sz = rystride; + else + a_sz = a_dim1; + + t1_dim = a_sz * 256 + b_dim1; if (t1_dim > 65536) t1_dim = 65536; @@ -2613,8 +2633,13 @@ matmul_i2 (gfc_array_i2 * const restrict retarray, return; /* Adjust size of t1 to what is needed. */ - index_type t1_dim; - t1_dim = (a_dim1 - (ycount > 1)) * 256 + b_dim1; + index_type t1_dim, a_sz; + if (aystride == 1) + a_sz = rystride; + else + a_sz = a_dim1; + + t1_dim = a_sz * 256 + b_dim1; if (t1_dim > 65536) t1_dim = 65536; -- cgit v1.1