AArch64: Add NEON, SVE and SVE2 RTL patterns for Multiply, FMS and FMA.

This adds implementation for the optabs for complex operations.  With this the
following C code:

  void g (float complex a[restrict N], float complex b[restrict N],
	  float complex c[restrict N])
  {
    for (int i=0; i < N; i++)
      c[i] =  a[i] * b[i];
  }

generates

NEON:

g:
        movi    v3.4s, 0
        mov     x3, 0
        .p2align 3,,7
.L2:
        mov     v0.16b, v3.16b
        ldr     q2, [x1, x3]
        ldr     q1, [x0, x3]
        fcmla   v0.4s, v1.4s, v2.4s, #0
        fcmla   v0.4s, v1.4s, v2.4s, #90
        str     q0, [x2, x3]
        add     x3, x3, 16
        cmp     x3, 1600
        bne     .L2
        ret

SVE:

g:
        mov     x3, 0
        mov     x4, 400
        ptrue   p1.b, all
        whilelo p0.s, xzr, x4
        mov     z3.s, #0
        .p2align 3,,7
.L2:
        ld1w    z1.s, p0/z, [x0, x3, lsl 2]
        ld1w    z2.s, p0/z, [x1, x3, lsl 2]
        movprfx z0, z3
        fcmla   z0.s, p1/m, z1.s, z2.s, #0
        fcmla   z0.s, p1/m, z1.s, z2.s, #90
        st1w    z0.s, p0, [x2, x3, lsl 2]
        incw    x3
        whilelo p0.s, x3, x4
        b.any   .L2
        ret

SVE2 (with int instead of float)
g:
        mov     x3, 0
        mov     x4, 400
        mov     z3.b, #0
        whilelo p0.s, xzr, x4
        .p2align 3,,7
.L2:
        ld1w    z1.s, p0/z, [x0, x3, lsl 2]
        ld1w    z2.s, p0/z, [x1, x3, lsl 2]
        movprfx z0, z3
        cmla    z0.s, z1.s, z2.s, #0
        cmla    z0.s, z1.s, z2.s, #90
        st1w    z0.s, p0, [x2, x3, lsl 2]
        incw    x3
        whilelo p0.s, x3, x4
        b.any   .L2
        ret

gcc/ChangeLog:

	* config/aarch64/aarch64-simd.md (cml<fcmac1><conj_op><mode>4,
	cmul<conj_op><mode>3): New.
	* config/aarch64/iterators.md (UNSPEC_FCMUL,
	UNSPEC_FCMUL180, UNSPEC_FCMLA_CONJ, UNSPEC_FCMLA180_CONJ,
	UNSPEC_CMLA_CONJ, UNSPEC_CMLA180_CONJ, UNSPEC_CMUL, UNSPEC_CMUL180,
	FCMLA_OP, FCMUL_OP, conj_op, rotsplit1, rotsplit2, fcmac1, sve_rot1,
	sve_rot2, SVE2_INT_CMLA_OP, SVE2_INT_CMUL_OP, SVE2_INT_CADD_OP): New.
	(rot): Add UNSPEC_FCMUL, UNSPEC_FCMUL180.
	(rot_op): Renamed to conj_op.
	* config/aarch64/aarch64-sve.md (cml<fcmac1><conj_op><mode>4,
	cmul<conj_op><mode>3): New.
	* config/aarch64/aarch64-sve2.md (cml<fcmac1><conj_op><mode>4,
	cmul<conj_op><mode>3): New.

0 files changed, 0 insertions, 0 deletions