target/arm: Implement SVE2 Integer Multiply - Unpredicated

For MUL, we can rely on generic support.  For SMULH and UMULH,
create some trivial helpers.  For PMUL, back in a21bb78e58,
we organized helper_gvec_pmul_b in preparation for this use.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

target/arm/helper.h

@@ -828,6 +828,16 @@ DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(gvec_smulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_smulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_smulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_smulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_umulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_umulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_umulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_umulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

target/arm/sve.decode

@@ -1090,3 +1090,13 @@ ST1_zprz        1110010 .. 00 ..... 100 ... ..... ..... \
                 @rprr_scatter_store xs=0 esz=3 scale=0
 ST1_zprz        1110010 .. 00 ..... 110 ... ..... ..... \
                 @rprr_scatter_store xs=1 esz=3 scale=0
+
+#### SVE2 Support
+
+### SVE2 Integer Multiply - Unpredicated
+
+# SVE2 integer multiply vectors (unpredicated)
+MUL_zzz         00000100 .. 1 ..... 0110 00 ..... .....  @rd_rn_rm
+SMULH_zzz       00000100 .. 1 ..... 0110 10 ..... .....  @rd_rn_rm
+UMULH_zzz       00000100 .. 1 ..... 0110 11 ..... .....  @rd_rn_rm
+PMUL_zzz        00000100 00 1 ..... 0110 01 ..... .....  @rd_rn_rm_e0

target/arm/translate-sve.c

@@ -5795,3 +5795,53 @@ static bool trans_MOVPRFX_z(DisasContext *s, arg_rpr_esz *a)
 {
     return do_movz_zpz(s, a->rd, a->rn, a->pg, a->esz, false);
 }
+
+/*
+ * SVE2 Integer Multiply - Unpredicated
+ */
+
+static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_fn_zzz(s, tcg_gen_gvec_mul, a->esz, a->rd, a->rn, a->rm);
+    }
+    return true;
+}
+
+static bool do_sve2_zzz_ool(DisasContext *s, arg_rrr_esz *a,
+                            gen_helper_gvec_3 *fn)
+{
+    if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0);
+    }
+    return true;
+}
+
+static bool trans_SMULH_zzz(DisasContext *s, arg_rrr_esz *a)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h,
+        gen_helper_gvec_smulh_s, gen_helper_gvec_smulh_d,
+    };
+    return do_sve2_zzz_ool(s, a, fns[a->esz]);
+}
+
+static bool trans_UMULH_zzz(DisasContext *s, arg_rrr_esz *a)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_gvec_umulh_b, gen_helper_gvec_umulh_h,
+        gen_helper_gvec_umulh_s, gen_helper_gvec_umulh_d,
+    };
+    return do_sve2_zzz_ool(s, a, fns[a->esz]);
+}
+
+static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b);
+}

target/arm/vec_helper.c

@@ -1985,3 +1985,99 @@ void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc)
     clear_tail(vd, oprsz, simd_maxsz(desc));
 }
 #endif
+
+/*
+ * NxN -> N highpart multiply
+ *
+ * TODO: expose this as a generic vector operation.
+ */
+
+void HELPER(gvec_smulh_b)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int8_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = ((int32_t)n[i] * m[i]) >> 8;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_smulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int16_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 2; ++i) {
+        d[i] = ((int32_t)n[i] * m[i]) >> 16;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_smulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    int32_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = ((int64_t)n[i] * m[i]) >> 32;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_smulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint64_t *d = vd, *n = vn, *m = vm;
+    uint64_t discard;
+
+    for (i = 0; i < opr_sz / 8; ++i) {
+        muls64(&discard, &d[i], n[i], m[i]);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_umulh_b)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint8_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz; ++i) {
+        d[i] = ((uint32_t)n[i] * m[i]) >> 8;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_umulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint16_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 2; ++i) {
+        d[i] = ((uint32_t)n[i] * m[i]) >> 16;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_umulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint32_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = ((uint64_t)n[i] * m[i]) >> 32;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_umulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint64_t *d = vd, *n = vn, *m = vm;
+    uint64_t discard;
+
+    for (i = 0; i < opr_sz / 8; ++i) {
+        mulu64(&discard, &d[i], n[i], m[i]);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}