Split out a helper that can handle the 4-register
format for helpers shared with SVE.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/translate-neon.c.inc | 98 +++++++++++++++------------------
1 file changed, 43 insertions(+), 55 deletions(-)
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index 6f418bd8de..6385d13a7e 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -142,24 +142,21 @@ static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var)
}
}
-static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
+static bool do_neon_ddda_fpst(DisasContext *s, int q, int vd, int vn, int vm,
+ int data, ARMFPStatusFlavour fp_flavor,
+ gen_helper_gvec_4_ptr *fn_gvec_ptr)
{
- int opr_sz;
- TCGv_ptr fpst;
- gen_helper_gvec_4_ptr *fn_gvec_ptr;
-
- if (!dc_isar_feature(aa32_vcma, s)
- || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) {
- return false;
- }
-
/* UNDEF accesses to D16-D31 if they don't exist. */
- if (!dc_isar_feature(aa32_simd_r32, s) &&
- ((a->vd | a->vn | a->vm) & 0x10)) {
+ if (((vd | vn | vm) & 0x10) && !dc_isar_feature(aa32_simd_r32, s)) {
return false;
}
- if ((a->vn | a->vm | a->vd) & a->q) {
+ /*
+ * UNDEF accesses to odd registers for each bit of Q.
+ * Q will be 0b111 for all Q-reg instructions, otherwise
+ * when we have mixed Q- and D-reg inputs.
+ */
+ if (((vd & 1) * 4 | (vn & 1) * 2 | (vm & 1)) & q) {
return false;
}
@@ -167,20 +164,34 @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
return true;
}
- opr_sz = (1 + a->q) * 8;
- fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
- fn_gvec_ptr = (a->size == MO_16) ?
- gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas;
- tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd),
- vfp_reg_offset(1, a->vn),
- vfp_reg_offset(1, a->vm),
- vfp_reg_offset(1, a->vd),
- fpst, opr_sz, opr_sz, a->rot,
- fn_gvec_ptr);
+ int opr_sz = q ? 16 : 8;
+ TCGv_ptr fpst = fpstatus_ptr(fp_flavor);
+
+ tcg_gen_gvec_4_ptr(vfp_reg_offset(1, vd),
+ vfp_reg_offset(1, vn),
+ vfp_reg_offset(1, vm),
+ vfp_reg_offset(1, vd),
+ fpst, opr_sz, opr_sz, data, fn_gvec_ptr);
tcg_temp_free_ptr(fpst);
return true;
}
+static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
+{
+ if (!dc_isar_feature(aa32_vcma, s)) {
+ return false;
+ }
+ if (a->size == MO_16) {
+ if (!dc_isar_feature(aa32_fp16_arith, s)) {
+ return false;
+ }
+ return do_neon_ddda_fpst(s, a->q * 7, a->vd, a->vn, a->vm, a->rot,
+ FPST_STD_F16, gen_helper_gvec_fcmlah);
+ }
+ return do_neon_ddda_fpst(s, a->q * 7, a->vd, a->vn, a->vm, a->rot,
+ FPST_STD, gen_helper_gvec_fcmlas);
+}
+
static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
{
int opr_sz;
@@ -285,43 +296,20 @@ static bool trans_VFML(DisasContext *s, arg_VFML *a)
static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
{
- gen_helper_gvec_4_ptr *fn_gvec_ptr;
- int opr_sz;
- TCGv_ptr fpst;
+ int data = (a->index << 2) | a->rot;
if (!dc_isar_feature(aa32_vcma, s)) {
return false;
}
- if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) {
- return false;
+ if (a->size == MO_16) {
+ if (!dc_isar_feature(aa32_fp16_arith, s)) {
+ return false;
+ }
+ return do_neon_ddda_fpst(s, a->q * 6, a->vd, a->vn, a->vm, data,
+ FPST_STD_F16, gen_helper_gvec_fcmlah_idx);
}
-
- /* UNDEF accesses to D16-D31 if they don't exist. */
- if (!dc_isar_feature(aa32_simd_r32, s) &&
- ((a->vd | a->vn | a->vm) & 0x10)) {
- return false;
- }
-
- if ((a->vd | a->vn) & a->q) {
- return false;
- }
-
- if (!vfp_access_check(s)) {
- return true;
- }
-
- fn_gvec_ptr = (a->size == MO_16) ?
- gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx;
- opr_sz = (1 + a->q) * 8;
- fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
- tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd),
- vfp_reg_offset(1, a->vn),
- vfp_reg_offset(1, a->vm),
- vfp_reg_offset(1, a->vd),
- fpst, opr_sz, opr_sz,
- (a->index << 2) | a->rot, fn_gvec_ptr);
- tcg_temp_free_ptr(fpst);
- return true;
+ return do_neon_ddda_fpst(s, a->q * 6, a->vd, a->vn, a->vm, data,
+ FPST_STD, gen_helper_gvec_fcmlas_idx);
}
static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
--
2.25.1