===================================================================
@@ -7442,6 +7442,9 @@ rs6000_expand_vector_set (rtx target, rt
else if (mode == V2DImode)
insn = gen_vsx_set_v2di (target, target, val, elt_rtx);
+ else if (TARGET_P9_VECTOR && mode == V4SFmode)
+ insn = gen_vsx_set_v4sf_p9 (target, target, val, elt_rtx);
+
else if (TARGET_P9_VECTOR && TARGET_VSX_SMALL_INTEGER
&& TARGET_UPPER_REGS_DI && TARGET_POWERPC64)
{
===================================================================
@@ -3012,6 +3012,105 @@ (define_insn "vsx_set_<mode>_p9"
}
[(set_attr "type" "vecperm")])
+(define_insn_and_split "vsx_set_v4sf_p9"
+ [(set (match_operand:V4SF 0 "gpc_reg_operand" "=wa")
+ (unspec:V4SF
+ [(match_operand:V4SF 1 "gpc_reg_operand" "0")
+ (match_operand:SF 2 "gpc_reg_operand" "ww")
+ (match_operand:QI 3 "const_0_to_3_operand" "n")]
+ UNSPEC_VSX_SET))
+ (clobber (match_scratch:SI 4 "=&wJwK"))]
+ "VECTOR_MEM_VSX_P (V4SFmode) && TARGET_P9_VECTOR"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 5)
+ (unspec:V4SF [(match_dup 2)]
+ UNSPEC_VSX_CVDPSPN))
+ (parallel [(set (match_dup 4)
+ (vec_select:SI (match_dup 6)
+ (parallel [(match_dup 7)])))
+ (clobber (scratch:SI))])
+ (set (match_dup 8)
+ (unspec:V4SI [(match_dup 8)
+ (match_dup 4)
+ (match_dup 3)]
+ UNSPEC_VSX_SET))]
+{
+ unsigned int tmp_regno = reg_or_subregno (operands[4]);
+
+ operands[5] = gen_rtx_REG (V4SFmode, tmp_regno);
+ operands[6] = gen_rtx_REG (V4SImode, tmp_regno);
+ operands[7] = GEN_INT (VECTOR_ELT_ORDER_BIG ? 1 : 2);
+ operands[8] = gen_rtx_REG (V4SImode, reg_or_subregno (operands[0]));
+}
+ [(set_attr "type" "vecperm")
+ (set_attr "length" "12")])
+
+;; Optimize x = vec_insert (vec_extract (v2, n), v1, m) if n is the element
+;; that is in the default scalar position (1 for big endian, 2 for little
+;; endian). We just need to do an xxinsertw since the element is in the
+;; correct location.
+
+(define_insn "*vsx_insert_extract_v4sf_p9"
+ [(set (match_operand:V4SF 0 "gpc_reg_operand" "=wa")
+ (unspec:V4SF
+ [(match_operand:V4SF 1 "gpc_reg_operand" "0")
+ (vec_select:SF (match_operand:V4SF 2 "gpc_reg_operand" "wa")
+ (parallel
+ [(match_operand:QI 3 "const_0_to_3_operand" "n")]))
+ (match_operand:QI 4 "const_0_to_3_operand" "n")]
+ UNSPEC_VSX_SET))]
+ "VECTOR_MEM_VSX_P (V4SFmode) && TARGET_P9_VECTOR
+ && (INTVAL (operands[3]) == (VECTOR_ELT_ORDER_BIG ? 1 : 2))"
+{
+ int ele = INTVAL (operands[4]);
+
+ if (!VECTOR_ELT_ORDER_BIG)
+ ele = GET_MODE_NUNITS (V4SFmode) - 1 - ele;
+
+ operands[4] = GEN_INT (GET_MODE_SIZE (SFmode) * ele);
+ return "xxinsertw %x0,%x2,%4";
+}
+ [(set_attr "type" "vecperm")])
+
+;; Optimize x = vec_insert (vec_extract (v2, n), v1, m) if n is not the element
+;; that is in the default scalar position (1 for big endian, 2 for little
+;; endian). Convert the insert/extract to int and avoid doing the conversion.
+
+(define_insn_and_split "*vsx_insert_extract_v4sf_p9_2"
+ [(set (match_operand:V4SF 0 "gpc_reg_operand" "=wa")
+ (unspec:V4SF
+ [(match_operand:V4SF 1 "gpc_reg_operand" "0")
+ (vec_select:SF (match_operand:V4SF 2 "gpc_reg_operand" "wa")
+ (parallel
+ [(match_operand:QI 3 "const_0_to_3_operand" "n")]))
+ (match_operand:QI 4 "const_0_to_3_operand" "n")]
+ UNSPEC_VSX_SET))
+ (clobber (match_scratch:SI 5 "=&wJwK"))]
+ "VECTOR_MEM_VSX_P (V4SFmode) && VECTOR_MEM_VSX_P (V4SImode)
+ && TARGET_P9_VECTOR && TARGET_VSX_SMALL_INTEGER
+ && (INTVAL (operands[3]) != (VECTOR_ELT_ORDER_BIG ? 1 : 2))"
+ "#"
+ "&& 1"
+ [(parallel [(set (match_dup 5)
+ (vec_select:SI (match_dup 6)
+ (parallel [(match_dup 3)])))
+ (clobber (scratch:SI))])
+ (set (match_dup 7)
+ (unspec:V4SI [(match_dup 8)
+ (match_dup 5)
+ (match_dup 4)]
+ UNSPEC_VSX_SET))]
+{
+ if (GET_CODE (operands[5]) == SCRATCH)
+ operands[5] = gen_reg_rtx (SImode);
+
+ operands[6] = gen_lowpart (V4SImode, operands[2]);
+ operands[7] = gen_lowpart (V4SImode, operands[0]);
+ operands[8] = gen_lowpart (V4SImode, operands[1]);
+}
+ [(set_attr "type" "vecperm")])
+
;; Expanders for builtins
(define_expand "vsx_mergel_<mode>"
[(use (match_operand:VSX_D 0 "vsx_register_operand" ""))
===================================================================
@@ -0,0 +1,41 @@
+/* { dg-do compile { target { powerpc64*-*-* && lp64 } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-mcpu=power9 -O2" } */
+
+#include <altivec.h>
+
+/* GCC 7.1 did not have a specialized method for inserting 32-bit floating point on
+ ISA 3.0 (power9) systems. */
+
+vector float
+insert_arg_0 (vector float vf, float f)
+{
+ return vec_insert (f, vf, 0);
+}
+
+vector float
+insert_arg_1 (vector float vf, float f)
+{
+ return vec_insert (f, vf, 1);
+}
+
+vector float
+insert_arg_2 (vector float vf, float f)
+{
+ return vec_insert (f, vf, 2);
+}
+
+vector float
+insert_arg_3 (vector float vf, float f)
+{
+ return vec_insert (f, vf, 3);
+}
+
+/* { dg-final { scan-assembler-not {\mlvewx\M} } } */
+/* { dg-final { scan-assembler-not {\mlvx\M} } } */
+/* { dg-final { scan-assembler-not {\mvperm\M} } } */
+/* { dg-final { scan-assembler-not {\mvpermr\M} } } */
+/* { dg-final { scan-assembler-not {\mstfs\M} } } */
+/* { dg-final { scan-assembler-not {\mstxssp\M} } } */
+/* { dg-final { scan-assembler-not {\mstxsspx\M} } } */
===================================================================
@@ -0,0 +1,31 @@
+/* { dg-do compile { target { powerpc64*-*-* && lp64 } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-mcpu=power9 -O2" } */
+
+#include <altivec.h>
+
+/* Optimize x = vec_insert (vec_extract (v2, N), v1, M) for SFmode if N is the default
+ scalar position. */
+
+#if __ORDER_LITTLE_ENDIAN__
+#define ELE 2
+#else
+#define ELE 1
+#endif
+
+vector float
+foo (vector float v1, vector float v2)
+{
+ return vec_insert (vec_extract (v2, ELE), v1, 0);
+}
+
+/* { dg-final { scan-assembler {\mxxinsertw\M} } } */
+/* { dg-final { scan-assembler-not {\mxxextractuw\M} } } */
+/* { dg-final { scan-assembler-not {\mlvewx\M} } } */
+/* { dg-final { scan-assembler-not {\mlvx\M} } } */
+/* { dg-final { scan-assembler-not {\mvperm\M} } } */
+/* { dg-final { scan-assembler-not {\mvpermr\M} } } */
+/* { dg-final { scan-assembler-not {\mstfs\M} } } */
+/* { dg-final { scan-assembler-not {\mstxssp\M} } } */
+/* { dg-final { scan-assembler-not {\mstxsspx\M} } } */
===================================================================
@@ -0,0 +1,24 @@
+/* { dg-do compile { target { powerpc64*-*-* && lp64 } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-mcpu=power9 -O2" } */
+
+#include <altivec.h>
+
+/* Optimize x = vec_insert (vec_extract (v2, N), v1, M) for SFmode. */
+
+vector float
+foo (vector float v1, vector float v2)
+{
+ return vec_insert (vec_extract (v2, 4), v1, 0);
+}
+
+/* { dg-final { scan-assembler {\mxxinsertw\M} } } */
+/* { dg-final { scan-assembler {\mxxextractuw\M} } } */
+/* { dg-final { scan-assembler-not {\mlvewx\M} } } */
+/* { dg-final { scan-assembler-not {\mlvx\M} } } */
+/* { dg-final { scan-assembler-not {\mvperm\M} } } */
+/* { dg-final { scan-assembler-not {\mvpermr\M} } } */
+/* { dg-final { scan-assembler-not {\mstfs\M} } } */
+/* { dg-final { scan-assembler-not {\mstxssp\M} } } */
+/* { dg-final { scan-assembler-not {\mstxsspx\M} } } */
===================================================================
@@ -0,0 +1,105 @@
+/* { dg-do run { target { powerpc*-*-linux* } } } */
+/* { dg-require-effective-target vsx_hw } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
+/* { dg-require-effective-target p9vector_hw } */
+/* { dg-options "-mcpu=power9 -O2" } */
+
+#include <altivec.h>
+#include <stdlib.h>
+
+__attribute__ ((__noinline__))
+vector float
+insert_0 (vector float v, float f)
+{
+ return vec_insert (f, v, 0);
+}
+
+__attribute__ ((__noinline__))
+vector float
+insert_1 (vector float v, float f)
+{
+ return vec_insert (f, v, 1);
+}
+
+__attribute__ ((__noinline__))
+vector float
+insert_2 (vector float v, float f)
+{
+ return vec_insert (f, v, 2);
+}
+
+__attribute__ ((__noinline__))
+vector float
+insert_3 (vector float v, float f)
+{
+ return vec_insert (f, v, 3);
+}
+
+__attribute__ ((__noinline__))
+void
+test_insert (void)
+{
+ vector float v1 = { 1.0f, 2.0f, 3.0f, 4.0f };
+ vector float v2 = { 5.0f, 6.0f, 7.0f, 8.0f };
+
+ v1 = insert_0 (v1, 5.0f);
+ v1 = insert_1 (v1, 6.0f);
+ v1 = insert_2 (v1, 7.0f);
+ v1 = insert_3 (v1, 8.0f);
+
+ if (vec_any_ne (v1, v2))
+ abort ();
+}
+
+__attribute__ ((__noinline__))
+vector float
+insert_extract_0_3 (vector float v1, vector float v2)
+{
+ return vec_insert (vec_extract (v2, 3), v1, 0);
+}
+
+__attribute__ ((__noinline__))
+vector float
+insert_extract_1_2 (vector float v1, vector float v2)
+{
+ return vec_insert (vec_extract (v2, 2), v1, 1);
+}
+
+__attribute__ ((__noinline__))
+vector float
+insert_extract_2_1 (vector float v1, vector float v2)
+{
+ return vec_insert (vec_extract (v2, 1), v1, 2);
+}
+
+__attribute__ ((__noinline__))
+vector float
+insert_extract_3_0 (vector float v1, vector float v2)
+{
+ return vec_insert (vec_extract (v2, 0), v1, 3);
+}
+
+__attribute__ ((__noinline__))
+void
+test_insert_extract (void)
+{
+ vector float v1 = { 1.0f, 2.0f, 3.0f, 4.0f };
+ vector float v2 = { 5.0f, 6.0f, 7.0f, 8.0f };
+ vector float v3 = { 8.0f, 7.0f, 6.0f, 5.0f };
+
+ v1 = insert_extract_0_3 (v1, v2);
+ v1 = insert_extract_1_2 (v1, v2);
+ v1 = insert_extract_2_1 (v1, v2);
+ v1 = insert_extract_3_0 (v1, v2);
+
+ if (vec_any_ne (v1, v3))
+ abort ();
+}
+
+int
+main (void)
+{
+ test_insert ();
+ test_insert_extract ();
+ return 0;
+}