target/arm: Implement SVE load and broadcast element

Backports commit 684598640dc3b28f86ccc28cc9af50ba257f4cc8 from qemu

qemu/aarch64.h

@@ -3660,6 +3660,10 @@
 #define helper_sve_mls_d helper_sve_mls_d_aarch64
 #define helper_sve_mls_h helper_sve_mls_h_aarch64
 #define helper_sve_mls_s helper_sve_mls_s_aarch64
+#define helper_sve_movz_b helper_sve_movz_b_aarch64
+#define helper_sve_movz_d helper_sve_movz_d_aarch64
+#define helper_sve_movz_h helper_sve_movz_h_aarch64
+#define helper_sve_movz_s helper_sve_movz_s_aarch64
 #define helper_sve_mul_zpzz_b helper_sve_mul_zpzz_b_aarch64
 #define helper_sve_mul_zpzz_d helper_sve_mul_zpzz_d_aarch64
 #define helper_sve_mul_zpzz_h helper_sve_mul_zpzz_h_aarch64

qemu/aarch64eb.h

@@ -3660,6 +3660,10 @@
 #define helper_sve_mls_d helper_sve_mls_d_aarch64eb
 #define helper_sve_mls_h helper_sve_mls_h_aarch64eb
 #define helper_sve_mls_s helper_sve_mls_s_aarch64eb
+#define helper_sve_movz_b helper_sve_movz_b_aarch64eb
+#define helper_sve_movz_d helper_sve_movz_d_aarch64eb
+#define helper_sve_movz_h helper_sve_movz_h_aarch64eb
+#define helper_sve_movz_s helper_sve_movz_s_aarch64eb
 #define helper_sve_mul_zpzz_b helper_sve_mul_zpzz_b_aarch64eb
 #define helper_sve_mul_zpzz_d helper_sve_mul_zpzz_d_aarch64eb
 #define helper_sve_mul_zpzz_h helper_sve_mul_zpzz_h_aarch64eb

qemu/header_gen.py

@@ -3681,6 +3681,10 @@ aarch64_symbols = (
     'helper_sve_mls_d',
     'helper_sve_mls_h',
     'helper_sve_mls_s',
+    'helper_sve_movz_b',
+    'helper_sve_movz_d',
+    'helper_sve_movz_h',
+    'helper_sve_movz_s',
     'helper_sve_mul_zpzz_b',
     'helper_sve_mul_zpzz_d',
     'helper_sve_mul_zpzz_h',

qemu/target/arm/helper-sve.h

@@ -274,6 +274,11 @@ DEF_HELPER_FLAGS_3(sve_clr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve_clr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve_clr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(sve_movz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_movz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_movz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_movz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(sve_asr_zpzi_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve_asr_zpzi_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve_asr_zpzi_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

qemu/target/arm/sve.decode

@@ -28,6 +28,7 @@
 %imm8_16_10     16:5 10:3
 %imm9_16_10     16:s6 10:3
 %size_23        23:2
+%dtype_23_13    23:2 13:2
 
 # A combination of tsz:imm3 -- extract esize.
 %tszimm_esz     22:2 5:5 !function=tszimm_esz
@@ -751,6 +752,10 @@ LDR_pri         10000101 10 ...... 000 ... ..... 0 ....         @pd_rn_i9
 # SVE load vector register
 LDR_zri         10000101 10 ...... 010 ... ..... .....          @rd_rn_i9
 
+# SVE load and broadcast element
+LD1R_zpri       1000010 .. 1 imm:6 1.. pg:3 rn:5 rd:5 \
+                &rpri_load dtype=%dtype_23_13 nreg=0
+
 ### SVE Memory Contiguous Load Group
 
 # SVE contiguous load (scalar plus scalar)

qemu/target/arm/sve_helper.c

@@ -994,6 +994,47 @@ void HELPER(sve_clr_d)(void *vd, void *vg, uint32_t desc)
     }
 }
 
+/* Copy Zn into Zd, and store zero into inactive elements.  */
+void HELPER(sve_movz_b)(void *vd, void *vn, void *vg, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn;
+    uint8_t *pg = vg;
+    for (i = 0; i < opr_sz; i += 1) {
+        d[i] = n[i] & expand_pred_b(pg[H1(i)]);
+    }
+}
+
+void HELPER(sve_movz_h)(void *vd, void *vn, void *vg, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn;
+    uint8_t *pg = vg;
+    for (i = 0; i < opr_sz; i += 1) {
+        d[i] = n[i] & expand_pred_h(pg[H1(i)]);
+    }
+}
+
+void HELPER(sve_movz_s)(void *vd, void *vn, void *vg, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn;
+    uint8_t *pg = vg;
+    for (i = 0; i < opr_sz; i += 1) {
+        d[i] = n[i] & expand_pred_s(pg[H1(i)]);
+    }
+}
+
+void HELPER(sve_movz_d)(void *vd, void *vn, void *vg, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc) / 8;
+    uint64_t *d = vd, *n = vn;
+    uint8_t *pg = vg;
+    for (i = 0; i < opr_sz; i += 1) {
+        d[i] = n[1] & -(uint64_t)(pg[H1(i)] & 1);
+    }
+}
+
 /* Three-operand expander, immediate operand, controlled by a predicate.
  */
 #define DO_ZPZI(NAME, TYPE, H, OP)                              \

qemu/target/arm/translate-sve.c

@@ -615,6 +615,21 @@ static bool do_clr_zp(DisasContext *s, int rd, int pg, int esz)
     return true;
 }
 
+/* Copy Zn into Zd, storing zeros into inactive elements.  */
+static void do_movz_zpz(DisasContext *s, int rd, int rn, int pg, int esz)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_sve_movz_b, gen_helper_sve_movz_h,
+        gen_helper_sve_movz_s, gen_helper_sve_movz_d,
+    };
+    TCGContext *tcg_ctx = s->uc->tcg_ctx;
+    unsigned vsz = vec_full_reg_size(s);
+    tcg_gen_gvec_3_ool(tcg_ctx, vec_full_reg_offset(s, rd),
+                       vec_full_reg_offset(s, rn),
+                       pred_full_reg_offset(s, pg),
+                       vsz, vsz, 0, fns[esz]);
+}
+
 static bool do_zpzi_ool(DisasContext *s, arg_rpri_esz *a,
                         gen_helper_gvec_3 *fn)
 {
@@ -4154,6 +4169,55 @@ static bool trans_LD1RQ_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
     return true;
 }
 
+/* Load and broadcast element.  */
+static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
+{
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    TCGContext *tcg_ctx = s->uc->tcg_ctx;
+    unsigned vsz = vec_full_reg_size(s);
+    unsigned psz = pred_full_reg_size(s);
+    unsigned esz = dtype_esz[a->dtype];
+    TCGLabel *over = gen_new_label(tcg_ctx);
+    TCGv_i64 temp;
+
+    /* If the guarding predicate has no bits set, no load occurs.  */
+    if (psz <= 8) {
+        /* Reduce the pred_esz_masks value simply to reduce the
+         * size of the code generated here.
+         */
+        uint64_t psz_mask = MAKE_64BIT_MASK(0, psz * 8);
+        temp = tcg_temp_new_i64(tcg_ctx);
+        tcg_gen_ld_i64(tcg_ctx, temp, tcg_ctx->cpu_env, pred_full_reg_offset(s, a->pg));
+        tcg_gen_andi_i64(tcg_ctx, temp, temp, pred_esz_masks[esz] & psz_mask);
+        tcg_gen_brcondi_i64(tcg_ctx, TCG_COND_EQ, temp, 0, over);
+        tcg_temp_free_i64(tcg_ctx, temp);
+    } else {
+        TCGv_i32 t32 = tcg_temp_new_i32(tcg_ctx);
+        find_last_active(s, t32, esz, a->pg);
+        tcg_gen_brcondi_i32(tcg_ctx, TCG_COND_LT, t32, 0, over);
+        tcg_temp_free_i32(tcg_ctx, t32);
+    }
+
+    /* Load the data.  */
+    temp = tcg_temp_new_i64(tcg_ctx);
+    tcg_gen_addi_i64(tcg_ctx, temp, cpu_reg_sp(s, a->rn), a->imm << esz);
+    tcg_gen_qemu_ld_i64(s->uc, temp, temp, get_mem_index(s),
+                        s->be_data | dtype_mop[a->dtype]);
+
+    /* Broadcast to *all* elements.  */
+    tcg_gen_gvec_dup_i64(tcg_ctx, esz, vec_full_reg_offset(s, a->rd),
+                         vsz, vsz, temp);
+    tcg_temp_free_i64(tcg_ctx, temp);
+
+    /* Zero the inactive elements.  */
+    gen_set_label(tcg_ctx, over);
+    do_movz_zpz(s, a->rd, a->rd, a->pg, esz);
+    return true;
+}
+
 static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
                       int msz, int esz, int nreg)
 {