As Richard pointed out in [1] and the testing on Power10, the
proposed fix for PR96373 requires some updates on a few rs6000
test cases which adopt partial vector. This patch is to fix
all of them with one extra option "-fno-trapping-math" as
Richard suggested.
Besides, the original test case also failed on Power10 without
Richard's proposed fix, this patch adds it together for a bit
better testing coverage.
[1] https://gcc.gnu.org/pipermail/gcc-patches/2023-January/610728.html
PR target/96373
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/p9-vec-length-epil-1.c: Add -fno-trapping-math.
* gcc.target/powerpc/p9-vec-length-epil-2.c: Likewise.
* gcc.target/powerpc/p9-vec-length-epil-3.c: Likewise.
* gcc.target/powerpc/p9-vec-length-epil-4.c: Likewise.
* gcc.target/powerpc/p9-vec-length-epil-5.c: Likewise.
* gcc.target/powerpc/p9-vec-length-epil-6.c: Likewise.
* gcc.target/powerpc/p9-vec-length-epil-8.c: Likewise.
* gcc.target/powerpc/p9-vec-length-full-1.c: Likewise.
* gcc.target/powerpc/p9-vec-length-full-2.c: Likewise.
* gcc.target/powerpc/p9-vec-length-full-3.c: Likewise.
* gcc.target/powerpc/p9-vec-length-full-4.c: Likewise.
* gcc.target/powerpc/p9-vec-length-full-5.c: Likewise.
* gcc.target/powerpc/p9-vec-length-full-6.c: Likewise.
* gcc.target/powerpc/p9-vec-length-full-8.c: Likewise.
* gcc.target/powerpc/pr96373.c: New test.
(cherry picked from commit
4f5a1198065dc078f8099db628da7b06a2666f34)
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=1" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
/* { dg-do compile { target { lp64 && powerpc_p9vector_ok } } } */
-/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops" } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fno-trapping-math" } */
/* { dg-additional-options "--param=vect-partial-vector-usage=2" } */
--- /dev/null
+/* { dg-do run { target { powerpc*-*-linux* } } } */
+/* { dg-options "-O2 -ftree-vectorize" } */
+
+/* Verify it can run successfully, especially on Power10 and later. */
+
+#define _GNU_SOURCE
+#include <fenv.h>
+
+__attribute__ ((noipa)) void
+div (double *d, double *s, int n)
+{
+ for (; n; n--, d++, s++)
+ *d = *d / *s;
+}
+
+int main()
+{
+ double d[] = {1,2,3,4,5,6,7,8,9,10,11};
+ double s[] = {11,10,9,8,7,6,5,4,3,2,1};
+
+ feenableexcept(FE_DIVBYZERO|FE_INVALID);
+ div(d, s, 11);
+
+ int i;
+ for (i = 0; i < 11; i++)
+ __builtin_printf(" %f", d[i]);
+
+ __builtin_printf("\n");
+
+ return 0;
+}