@@ -2191,3 +2191,12 @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
@@ -30,6 +30,8 @@
%size_23 23:2
%dtype_23_13 23:2 13:2
%index3_22_19 22:1 19:2
+%index3_19_11 19:2 11:1
+%index2_20_11 20:1 11:1
# A combination of tsz:imm3 -- extract esize.
%tszimm_esz 22:2 5:5 !function=tszimm_esz
@@ -263,6 +265,12 @@
@rrxr_d ........ 11 . index:1 rm:4 ...... rn:5 rd:5 \
&rrxr_esz ra=%reg_movprfx esz=3
+# Three registers and a scalar by index, wide
+@rrxw_s ........ 10 ... rm:3 ...... rn:5 rd:5 \
+ &rrxr_esz ra=%reg_movprfx index=%index3_19_11 esz=2
+@rrxw_d ........ 11 .. rm:4 ...... rn:5 rd:5 \
+ &rrxr_esz ra=%reg_movprfx index=%index2_20_11 esz=3
+
###########################################################################
# Instruction patterns. Grouped according to the SVE encodingindex.xhtml.
@@ -801,6 +809,16 @@ SQRDMLSH_zzxz_h 01000100 .. 1 ..... 000101 ..... ..... @rrxr_h
SQRDMLSH_zzxz_s 01000100 .. 1 ..... 000101 ..... ..... @rrxr_s
SQRDMLSH_zzxz_d 01000100 .. 1 ..... 000101 ..... ..... @rrxr_d
+# SVE2 saturating multiply-add (indexed)
+SQDMLALB_zzxw_s 01000100 .. 1 ..... 0010.0 ..... ..... @rrxw_s
+SQDMLALB_zzxw_d 01000100 .. 1 ..... 0010.0 ..... ..... @rrxw_d
+SQDMLALT_zzxw_s 01000100 .. 1 ..... 0010.1 ..... ..... @rrxw_s
+SQDMLALT_zzxw_d 01000100 .. 1 ..... 0010.1 ..... ..... @rrxw_d
+SQDMLSLB_zzxw_s 01000100 .. 1 ..... 0011.0 ..... ..... @rrxw_s
+SQDMLSLB_zzxw_d 01000100 .. 1 ..... 0011.0 ..... ..... @rrxw_d
+SQDMLSLT_zzxw_s 01000100 .. 1 ..... 0011.1 ..... ..... @rrxw_s
+SQDMLSLT_zzxw_d 01000100 .. 1 ..... 0011.1 ..... ..... @rrxw_d
+
# SVE2 integer multiply (indexed)
MUL_zzx_h 01000100 .. 1 ..... 111110 ..... ..... @rrx_h
MUL_zzx_s 01000100 .. 1 ..... 111110 ..... ..... @rrx_s
@@ -1530,6 +1530,36 @@ DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t, , DO_SQRDMLSH_D)
#undef DO_ZZXZ
+#define DO_ZZXW(NAME, TYPEW, TYPEN, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{ \
+ intptr_t i, j, oprsz = simd_oprsz(desc); \
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \
+ intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 1, 3); \
+ for (i = 0; i < oprsz; i += 16) { \
+ TYPEW mm = *(TYPEN *)(vm + i + idx); \
+ for (j = 0; j < 16; j += sizeof(TYPEW)) { \
+ TYPEW nn = *(TYPEN *)(vn + HN(i + j + sel)); \
+ TYPEW aa = *(TYPEW *)(va + HW(i + j)); \
+ *(TYPEW *)(vd + HW(i + j)) = OP(nn, mm, aa); \
+ } \
+ } \
+}
+
+#define DO_SQDMLAL_S(N, M, A) DO_SQADD_S(A, do_sqdmull_s(N, M))
+#define DO_SQDMLAL_D(N, M, A) do_sqadd_d(A, do_sqdmull_d(N, M))
+
+DO_ZZXW(sve2_sqdmlal_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLAL_S)
+DO_ZZXW(sve2_sqdmlal_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLAL_D)
+
+#define DO_SQDMLSL_S(N, M, A) DO_SQSUB_S(A, do_sqdmull_s(N, M))
+#define DO_SQDMLSL_D(N, M, A) do_sqsub_d(A, do_sqdmull_d(N, M))
+
+DO_ZZXW(sve2_sqdmlsl_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLSL_S)
+DO_ZZXW(sve2_sqdmlsl_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLSL_D)
+
+#undef DO_ZZXW
+
#define DO_BITPERM(NAME, TYPE, OP) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
{ \
@@ -3821,21 +3821,21 @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a)
* SVE Multiply - Indexed
*/
-static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a,
- gen_helper_gvec_4 *fn)
+static bool do_zzxz_data(DisasContext *s, arg_rrxr_esz *a,
+ gen_helper_gvec_4 *fn, int data)
{
if (fn == NULL) {
return false;
}
if (sve_access_check(s)) {
- gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index);
+ gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data);
}
return true;
}
#define DO_RRXR(NAME, FUNC) \
static bool NAME(DisasContext *s, arg_rrxr_esz *a) \
- { return do_zzxz_ool(s, a, FUNC); }
+ { return do_zzxz_data(s, a, FUNC, a->index); }
DO_RRXR(trans_SDOT_zzxw_s, gen_helper_gvec_sdot_idx_b)
DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h)
@@ -3870,18 +3870,18 @@ DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
#undef DO_SVE2_RRX
-static bool do_sve2_zzxz_ool(DisasContext *s, arg_rrxr_esz *a,
- gen_helper_gvec_4 *fn)
+static bool do_sve2_zzxz_data(DisasContext *s, arg_rrxr_esz *a,
+ gen_helper_gvec_4 *fn, int data)
{
if (!dc_isar_feature(aa64_sve2, s)) {
return false;
}
- return do_zzxz_ool(s, a, fn);
+ return do_zzxz_data(s, a, fn, data);
}
#define DO_SVE2_RRXR(NAME, FUNC) \
static bool NAME(DisasContext *s, arg_rrxr_esz *a) \
- { return do_sve2_zzxz_ool(s, a, FUNC); }
+ { return do_sve2_zzxz_data(s, a, FUNC, a->index); }
DO_SVE2_RRXR(trans_MLA_zzxz_h, gen_helper_gvec_mla_idx_h)
DO_SVE2_RRXR(trans_MLA_zzxz_s, gen_helper_gvec_mla_idx_s)
@@ -3901,6 +3901,22 @@ DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d)
#undef DO_SVE2_RRXR
+#define DO_SVE2_RRXR_TB(NAME, FUNC, TOP) \
+ static bool NAME(DisasContext *s, arg_rrxr_esz *a) \
+ { return do_sve2_zzxz_data(s, a, FUNC, (a->index << 1) | TOP); }
+
+DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, false)
+DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, false)
+DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, true)
+DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, true)
+
+DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, false)
+DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, false)
+DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, true)
+DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, true)
+
+#undef DO_SVE2_RRXR_TB
+
/*
*** SVE Floating Point Multiply-Add Indexed Group
*/
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-sve.h | 9 +++++++++ target/arm/sve.decode | 18 ++++++++++++++++++ target/arm/sve_helper.c | 30 ++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 32 ++++++++++++++++++++++++-------- 4 files changed, 81 insertions(+), 8 deletions(-) -- 2.25.1