diff options
author | Yiran Wang <yiran@google.com> | 2015-06-23 15:33:17 -0700 |
---|---|---|
committer | Yiran Wang <yiran@google.com> | 2015-06-29 10:56:28 -0700 |
commit | 1d9fec7937f45dde5e04cac966a2d9a12f2fc15a (patch) | |
tree | 3fbcd18a379a05fd6d43491a107e1f36bc61b185 /gcc-4.9/gcc/testsuite/gcc.target/powerpc/swaps-p8-15.c | |
parent | f378ebf14df0952eae870c9865bab8326aa8f137 (diff) | |
download | toolchain_gcc-1d9fec7937f45dde5e04cac966a2d9a12f2fc15a.zip toolchain_gcc-1d9fec7937f45dde5e04cac966a2d9a12f2fc15a.tar.gz toolchain_gcc-1d9fec7937f45dde5e04cac966a2d9a12f2fc15a.tar.bz2 |
Synchronize with google/gcc-4_9 to r224707 (from r214835)
Change-Id: I3d6f06fc613c8f8b6a82143dc44b7338483aac5d
Diffstat (limited to 'gcc-4.9/gcc/testsuite/gcc.target/powerpc/swaps-p8-15.c')
-rw-r--r-- | gcc-4.9/gcc/testsuite/gcc.target/powerpc/swaps-p8-15.c | 51 |
1 files changed, 51 insertions, 0 deletions
diff --git a/gcc-4.9/gcc/testsuite/gcc.target/powerpc/swaps-p8-15.c b/gcc-4.9/gcc/testsuite/gcc.target/powerpc/swaps-p8-15.c new file mode 100644 index 0000000..172e4bd --- /dev/null +++ b/gcc-4.9/gcc/testsuite/gcc.target/powerpc/swaps-p8-15.c @@ -0,0 +1,51 @@ +/* { dg-do compile { target { powerpc64le-*-* } } } */ +/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */ +/* { dg-options "-mcpu=power8 -O3" } */ +/* { dg-final { scan-assembler "lxvd2x" } } */ +/* { dg-final { scan-assembler "stxvd2x" } } */ +/* { dg-final { scan-assembler "xxspltw" } } */ + +/* Currently the analyze_swaps phase cannot optimize this loop because + of the presence of an UNSPEC_VSX_CVDPSPN. At such time as this is + handled, we need to add a 'scan-assembler-not "xxpermdi"' directive to + this test. */ +#include <altivec.h> +void abort(); + +#define N 4096 +#define M 10000000 +vector float ca[N][4] = {0}; +vector float cb[N][4] = {0}; +vector float cc[N][4] = {0}; + +__attribute__((noinline)) void foo () +{ + int i; + for (i = 0; i < N; i++) { + cc[i][0] = vec_mul(vec_splats(cb[i][0][0]), ca[i][0]); + cc[i][0] = vec_madd(cc[i][0],vec_splats(cb[i][0][1]), ca[i][1]); + cc[i][0] = vec_madd(cc[i][0],vec_splats(cb[i][0][2]), ca[i][2]); + cc[i][0] = vec_madd(cc[i][0],vec_splats(cb[i][0][3]), ca[i][3]); + + cc[i][1] = vec_mul(vec_splats(cb[i][1][0]), ca[i][0]); + cc[i][1] = vec_madd(cc[i][0],vec_splats(cb[i][1][1]), ca[i][1]); + cc[i][1] = vec_madd(cc[i][0],vec_splats(cb[i][1][2]), ca[i][2]); + cc[i][1] = vec_madd(cc[i][0],vec_splats(cb[i][1][3]), ca[i][3]); + + cc[i][2] = vec_mul(vec_splats(cb[i][2][0]), ca[i][0]); + cc[i][2] = vec_madd(cc[i][0],vec_splats(cb[i][2][1]), ca[i][1]); + cc[i][2] = vec_madd(cc[i][0],vec_splats(cb[i][2][2]), ca[i][2]); + cc[i][2] = vec_madd(cc[i][0],vec_splats(cb[i][2][3]), ca[i][3]); + + cc[i][3] = vec_mul(vec_splats(cb[i][3][0]), ca[i][0]); + cc[i][3] = vec_madd(cc[i][0],vec_splats(cb[i][3][1]), ca[i][1]); + cc[i][3] = vec_madd(cc[i][0],vec_splats(cb[i][3][2]), ca[i][2]); + cc[i][3] = vec_madd(cc[i][0],vec_splats(cb[i][3][3]), ca[i][3]); + } +} + +int main () +{ + foo (); + return 0; +} |