https://gcc.gnu.org/g:4ce2ca4ed9fee43f9fc7a99168a99d395736244b
commit 4ce2ca4ed9fee43f9fc7a99168a99d395736244b
Author: Michael Meissner <meiss...@linux.ibm.com>
Date: Sat Nov 2 00:11:55 2024 -0400
Add vector pair swap even and odd.
This patch adds 2 additional functions:
vpair_f32_swap_odd_even
vpair_f64_swap_odd_even
This swaps the odd and even elements in a vector pair. The intention is for
libraries that are doing complex multiply to be able to swap the real and
imaginary elements to do the multiply operation.
2024-11-01 Michael Meissner <meiss...@linux.ibm.com>
gcc/
* config/rs6000/vector-pair.h (vpair_f32_swap_odd_even): New
function.
(vpair_f64_swap_odd_even): Likewise.
Diff:
---
gcc/config/rs6000/vector-pair.h | 54 ++++++++++++++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/vpair-1.c | 13 +++++--
gcc/testsuite/gcc.target/powerpc/vpair-2.c | 13 +++++--
gcc/testsuite/gcc.target/powerpc/vpair-3.h | 26 ++++++++++++++
gcc/testsuite/gcc.target/powerpc/vpair-4.h | 26 ++++++++++++++
5 files changed, 128 insertions(+), 4 deletions(-)
diff --git a/gcc/config/rs6000/vector-pair.h b/gcc/config/rs6000/vector-pair.h
index ceb28c4e974c..848c876beffc 100644
--- a/gcc/config/rs6000/vector-pair.h
+++ b/gcc/config/rs6000/vector-pair.h
@@ -516,4 +516,58 @@ vpair_f32_nfms (vector_pair_f32_t *__r,
"xvnmsubasp",
__builtin_vsx_xvnmsubsp);
}
+
+
+/* Swap even/odd operations. */
+
+static inline void
+vpair_f32_swap_odd_even (vector_pair_f32_t *__r,
+ const vector_pair_f32_t *__a)
+{
+ vector unsigned long long __rotate = { 32, 32 };
+
+#if __MMA__ && !__VPAIR_NOP10__
+ /* Power10 vector pair support. */
+ __asm__ ("vrld %0,%1,%2\n\tvrld %L0,%L1,%2"
+ : "=v" (__r->__vpair)
+ : "v" (__a->__vpair), "v" (__rotate));
+
+#else
+ /* vector pair not available. */
+ vector unsigned long long *__r_ll = (vector unsigned long long *)__r;
+ vector unsigned long long *__a_ll = (vector unsigned long long *)__a;
+ __r_ll[0] = __builtin_vec_vrld (__a_ll[0], __rotate);
+ __r_ll[1] = __builtin_vec_vrld (__a_ll[1], __rotate);
+#endif /* power10/not power10. */
+}
+
+
+static inline void
+vpair_f64_swap_odd_even (vector_pair_f64_t *__r,
+ const vector_pair_f64_t *__a)
+{
+#if __MMA__ && !__VPAIR_NOP10__
+#if __VPAIR__USE_FPR__ || !__GNUC__ || (!__linux__ && !__ELF__)
+
+ /* Use vector pair and use %0 and %L0 on traditional FPR registers. */
+ __asm__ ("xxpermdi %0,%1,%1,2\n\txxpermdi %L0,%L1,%L1,2"
+ : "=d" (__r->__vpair)
+ : "d" (__a->__vpair));
+
+#else
+ /* Use vector pair and use %x0 and %x0+ on all VSX registers. */
+ __asm__ ("xxpermdi %x0,%x1,%x1,2\n\txxpermdi %x0+1,%x1+1,%x1+1,2"
+ : "=wa" (__r->__vpair)
+ : "wa" (__a->__vpair));
+#endif
+
+#else
+ /* vector pair not available. */
+ __r->__vp_f64[0]
+ = __builtin_vsx_xxpermdi_2df (__a->__vp_f64[0], __a->__vp_f64[0], 2);
+ __r->__vp_f64[1]
+ = __builtin_vsx_xxpermdi_2df (__a->__vp_f64[1], __a->__vp_f64[1], 2);
+#endif
+}
+
#endif /* _VECTOR_PAIR_H. */
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-1.c
b/gcc/testsuite/gcc.target/powerpc/vpair-1.c
index 55772cc44e31..f56e99a1d044 100644
--- a/gcc/testsuite/gcc.target/powerpc/vpair-1.c
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-1.c
@@ -124,8 +124,16 @@ test_nfms (vector_pair_f64_t *dest,
vpair_f64_nfms (dest, x, y, z);
}
-/* { dg-final { scan-assembler-times {\mlxvp\M} 26 } } */
-/* { dg-final { scan-assembler-times {\mstxvp\M} 13 } } */
+void
+test_swap (vector_pair_f64_t *dest,
+ vector_pair_f64_t *x)
+{
+ /* 1 lxvp, 2 xxpermdi, 1 stxvp. */
+ vpair_f64_swap_odd_even (dest, x);
+}
+
+/* { dg-final { scan-assembler-times {\mlxvp\M} 27 } } */
+/* { dg-final { scan-assembler-times {\mstxvp\M} 14 } } */
/* { dg-final { scan-assembler-times {\mxvabsdp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxvadddp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxvmadd.dp\M} 2 } } */
@@ -139,3 +147,4 @@ test_nfms (vector_pair_f64_t *dest,
/* { dg-final { scan-assembler-times {\mxvnmsub.dp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxvsqrtdp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxvsubdp\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxpermdi\M} 2 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-2.c
b/gcc/testsuite/gcc.target/powerpc/vpair-2.c
index 3030b0b33380..0f84a74e94a1 100644
--- a/gcc/testsuite/gcc.target/powerpc/vpair-2.c
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-2.c
@@ -124,8 +124,17 @@ test_nfms (vector_pair_f32_t *dest,
vpair_f32_nfms (dest, x, y, z);
}
-/* { dg-final { scan-assembler-times {\mlxvp\M} 26 } } */
-/* { dg-final { scan-assembler-times {\mstxvp\M} 13 } } */
+void
+test_swap (vector_pair_f32_t *dest,
+ vector_pair_f32_t *x)
+{
+ /* 1 lxvp, 2 xxpermdi, 1 stxvp. */
+ vpair_f32_swap_odd_even (dest, x);
+}
+
+/* { dg-final { scan-assembler-times {\mlxvp\M} 27 } } */
+/* { dg-final { scan-assembler-times {\mstxvp\M} 14 } } */
+/* { dg-final { scan-assembler-times {\mvrld\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxvabssp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxvaddsp\M} 2 } } */
/* { dg-final { scan-assembler-times {\mxvmadd.sp\M} 2 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-3.h
b/gcc/testsuite/gcc.target/powerpc/vpair-3.h
index e61ad23dd57e..656488dbb627 100644
--- a/gcc/testsuite/gcc.target/powerpc/vpair-3.h
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-3.h
@@ -219,6 +219,19 @@ vpair_nfms (double *r, double *a, double *b, double *c,
size_t num)
vpair_f64_nfms (vr + i, va + i, vb + i, vc + i);
}
+void
+vpair_swap (double *r, double *a, double *b, double *c, size_t num)
+{
+ vector_pair_f64_t *vr = (vector_pair_f64_t *)r;
+ vector_pair_f64_t *va = (vector_pair_f64_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f64_t) / sizeof (double));
+
+ for (i = 0; i < num2; i++)
+ vpair_f64_swap_odd_even (vr + i, va + i);
+}
+
/* scalar tests. */
@@ -347,6 +360,18 @@ scalar_nfms (double *r, double *a, double *b, double *c,
size_t num)
for (i = 0; i < num; i++)
r[i] = - __builtin_fma (a[i], b[i], -c[i]);
}
+
+void
+scalar_swap (double *r, double *a, double *b, double *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i += 2)
+ {
+ r[i] = a[i+1];
+ r[i+1] = a[i];
+ }
+}
/* Check results. */
@@ -397,6 +422,7 @@ struct
{ vpair_fms, scalar_fms, "fms" },
{ vpair_nfma, scalar_nfma, "nfma" },
{ vpair_nfms, scalar_nfms, "nfms" },
+ { vpair_swap, scalar_swap, "swap" },
};
/* Run tests. */
diff --git a/gcc/testsuite/gcc.target/powerpc/vpair-4.h
b/gcc/testsuite/gcc.target/powerpc/vpair-4.h
index 1a80cf5e639a..49384e279740 100644
--- a/gcc/testsuite/gcc.target/powerpc/vpair-4.h
+++ b/gcc/testsuite/gcc.target/powerpc/vpair-4.h
@@ -219,6 +219,19 @@ vpair_nfms (float *r, float *a, float *b, float *c, size_t
num)
vpair_f32_nfms (vr + i, va + i, vb + i, vc + i);
}
+void
+vpair_swap (float *r, float *a, float *b, float *c, size_t num)
+{
+ vector_pair_f32_t *vr = (vector_pair_f32_t *)r;
+ vector_pair_f32_t *va = (vector_pair_f32_t *)a;
+
+ size_t i;
+ size_t num2 = num / (sizeof (vector_pair_f32_t) / sizeof (float));
+
+ for (i = 0; i < num2; i++)
+ vpair_f32_swap_odd_even (vr + i, va + i);
+}
+
/* scalar tests. */
@@ -347,6 +360,18 @@ scalar_nfms (float *r, float *a, float *b, float *c,
size_t num)
for (i = 0; i < num; i++)
r[i] = - __builtin_fma (a[i], b[i], -c[i]);
}
+
+void
+scalar_swap (float *r, float *a, float *b, float *c, size_t num)
+{
+ size_t i;
+
+ for (i = 0; i < num; i += 2)
+ {
+ r[i] = a[i+1];
+ r[i+1] = a[i];
+ }
+}
/* Check results. */
@@ -397,6 +422,7 @@ struct
{ vpair_fms, scalar_fms, "fms" },
{ vpair_nfma, scalar_nfma, "nfma" },
{ vpair_nfms, scalar_nfms, "nfms" },
+ { vpair_swap, scalar_swap, "swap" },
};
/* Run tests. */
