diff mbox series

[v2,098/101] target/arm: Implement MOVAZ for SME2p1

Message ID 20250621235037.74091-99-richard.henderson@linaro.org
State New
Headers show
Series target/arm: Implement FEAT_SME2p1 | expand

Commit Message

Richard Henderson June 21, 2025, 11:50 p.m. UTC 
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  6 ++++
 target/arm/tcg/sme_helper.c    | 60 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 46 +++++++++++++++++++-------
 target/arm/tcg/sme.decode      | 36 ++++++++++++++++++++
 4 files changed, 137 insertions(+), 11 deletions(-)
diff mbox series

Patch

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index d86fdcbd83..3e2ae83fe5 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -42,6 +42,12 @@  DEF_HELPER_FLAGS_3(sme2_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sme2_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sme2_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
 DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
 DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 7757085adf..16bdf61f51 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -250,6 +250,66 @@  void HELPER(sme2_mova_zc_d)(void *vdst, void *vsrc, uint32_t desc)
     }
 }
 
+void HELPER(sme2p1_movaz_zc_b)(void *vdst, void *vsrc, uint32_t desc)
+{
+    uint8_t *src = vsrc;
+    uint8_t *dst = vdst;
+    size_t i, n = simd_oprsz(desc);
+
+    for (i = 0; i < n; ++i) {
+        dst[i] = src[tile_vslice_index(i)];
+        src[tile_vslice_index(i)] = 0;
+    }
+}
+
+void HELPER(sme2p1_movaz_zc_h)(void *vdst, void *vsrc, uint32_t desc)
+{
+    uint16_t *src = vsrc;
+    uint16_t *dst = vdst;
+    size_t i, n = simd_oprsz(desc) / 2;
+
+    for (i = 0; i < n; ++i) {
+        dst[i] = src[tile_vslice_index(i)];
+        src[tile_vslice_index(i)] = 0;
+    }
+}
+
+void HELPER(sme2p1_movaz_zc_s)(void *vdst, void *vsrc, uint32_t desc)
+{
+    uint32_t *src = vsrc;
+    uint32_t *dst = vdst;
+    size_t i, n = simd_oprsz(desc) / 4;
+
+    for (i = 0; i < n; ++i) {
+        dst[i] = src[tile_vslice_index(i)];
+        src[tile_vslice_index(i)] = 0;
+    }
+}
+
+void HELPER(sme2p1_movaz_zc_d)(void *vdst, void *vsrc, uint32_t desc)
+{
+    uint64_t *src = vsrc;
+    uint64_t *dst = vdst;
+    size_t i, n = simd_oprsz(desc) / 8;
+
+    for (i = 0; i < n; ++i) {
+        dst[i] = src[tile_vslice_index(i)];
+        src[tile_vslice_index(i)] = 0;
+    }
+}
+
+void HELPER(sme2p1_movaz_zc_q)(void *vdst, void *vsrc, uint32_t desc)
+{
+    Int128 *src = vsrc;
+    Int128 *dst = vdst;
+    size_t i, n = simd_oprsz(desc) / 16;
+
+    for (i = 0; i < n; ++i) {
+        dst[i] = src[tile_vslice_index(i)];
+        memset(&src[tile_vslice_index(i)], 0, 16);
+    }
+}
+
 /*
  * Clear elements in a tile slice comprising len bytes.
  */
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 397e328a1b..12d32e3620 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -232,7 +232,8 @@  static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
 TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false)
 TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true)
 
-static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
+static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n,
+                           bool to_vec, bool zero)
 {
     static gen_helper_gvec_2 * const cz_fns[] = {
         gen_helper_sme2_mova_cz_b, gen_helper_sme2_mova_cz_h,
@@ -242,9 +243,16 @@  static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
         gen_helper_sme2_mova_zc_b, gen_helper_sme2_mova_zc_h,
         gen_helper_sme2_mova_zc_s, gen_helper_sme2_mova_zc_d,
     };
+    static gen_helper_gvec_2 * const zc_z_fns[] = {
+        gen_helper_sme2p1_movaz_zc_b, gen_helper_sme2p1_movaz_zc_h,
+        gen_helper_sme2p1_movaz_zc_s, gen_helper_sme2p1_movaz_zc_d,
+        gen_helper_sme2p1_movaz_zc_q,
+    };
     TCGv_ptr t_za;
     int svl;
 
+    assert(a->esz <= MO_64 + zero);
+
     if (!sme_smza_enabled_check(s)) {
         return true;
     }
@@ -262,7 +270,9 @@  static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
             TCGv_ptr t_zr = vec_full_reg_ptr(s, a->zr * n + i);
             t_za = get_tile_rowcol(s, a->esz, a->rs, a->za,
                                    a->off * n + i, 1, a->v);
-            if (to_vec) {
+            if (zero) {
+                zc_z_fns[a->esz](t_zr, t_za, t_desc);
+            } else if (to_vec) {
                 zc_fns[a->esz](t_zr, t_za, t_desc);
             } else {
                 cz_fns[a->esz](t_za, t_zr, t_desc);
@@ -275,6 +285,9 @@  static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
                                    a->off * n + i, 1, a->v);
             if (to_vec) {
                 tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, 0, svl, svl);
+                if (zero) {
+                    tcg_gen_gvec_dup_imm_var(MO_8, t_za, 0, svl, svl, 0);
+                }
             } else {
                 tcg_gen_gvec_mov_var(MO_8, t_za, 0, tcg_env, o_zr, svl, svl);
             }
@@ -283,12 +296,17 @@  static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
     return true;
 }
 
-TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false)
-TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false)
-TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true)
-TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true)
+TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false, false)
+TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false, false)
+TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true, false)
+TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true, false)
 
-static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
+TRANS_FEAT(MOVAZ_zt, aa64_sme2p1, do_mova_tile_n, a, 1, true, true)
+TRANS_FEAT(MOVAZ_zt2, aa64_sme2p1, do_mova_tile_n, a, 2, true, true)
+TRANS_FEAT(MOVAZ_zt4, aa64_sme2p1, do_mova_tile_n, a, 4, true, true)
+
+static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n,
+                            bool to_vec, bool zero)
 {
     TCGv_ptr t_za;
     int svl;
@@ -306,6 +324,9 @@  static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
 
         if (to_vec) {
             tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl);
+            if (zero) {
+                tcg_gen_gvec_dup_imm_var(MO_8, t_za, o_za, svl, svl, 0);
+            }
         } else {
             tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl);
         }
@@ -313,10 +334,13 @@  static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
     return true;
 }
 
-TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false)
-TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false)
-TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true)
-TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true)
+TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false, false)
+TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false, false)
+TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true, false)
+TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true, false)
+
+TRANS_FEAT(MOVAZ_za2, aa64_sme2p1, do_mova_array_n, a, 2, true, true)
+TRANS_FEAT(MOVAZ_za4, aa64_sme2p1, do_mova_array_n, a, 4, true, true)
 
 static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
                     void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 9740d74410..94e8653b89 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -100,6 +100,42 @@  MOVA_za2        11000000 00 00011 00 .. 010 00 off:3 zr:4 0  \
 MOVA_za4        11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \
                 &mova_a rv=%mova_rv
 
+### SME Move and Zero
+
+MOVAZ_za2       11000000 00000110 0 .. 01010 off:3 zr:4 0    \
+                &mova_a rv=%mova_rv
+MOVAZ_za4       11000000 00000110 0 .. 01110 off:3 zr:3 00   \
+                &mova_a rv=%mova_rv
+
+MOVAZ_zt        11000000 00 00001 0 v:1 .. 0001 off:4 zr:5    \
+                &mova_t rs=%mova_rs esz=0 za=0
+MOVAZ_zt        11000000 01 00001 0 v:1 .. 0001 za:1 off:3 zr:5    \
+                &mova_t rs=%mova_rs esz=1
+MOVAZ_zt        11000000 10 00001 0 v:1 .. 0001 za:2 off:2 zr:5    \
+                &mova_t rs=%mova_rs esz=2
+MOVAZ_zt        11000000 11 00001 0 v:1 .. 0001 za:3 off:1 zr:5    \
+                &mova_t rs=%mova_rs esz=3
+MOVAZ_zt        11000000 11 00001 1 v:1 .. 0001 za:4 zr:5    \
+                &mova_t rs=%mova_rs esz=4 off=0
+
+MOVAZ_zt2       11000000 00 00011 0 v:1 .. 00010 off:3 zr:4 0 \
+                &mova_t rs=%mova_rs esz=0 za=0
+MOVAZ_zt2       11000000 01 00011 0 v:1 .. 00010 za:1 off:2 zr:4 0 \
+                &mova_t rs=%mova_rs esz=1
+MOVAZ_zt2       11000000 10 00011 0 v:1 .. 00010 za:2 off:1 zr:4 0 \
+                &mova_t rs=%mova_rs esz=2
+MOVAZ_zt2       11000000 11 00011 0 v:1 .. 00010 za:3 zr:4 0 \
+                &mova_t rs=%mova_rs esz=3 off=0
+
+MOVAZ_zt4       11000000 00 00011 0 v:1 .. 001100 off:2 zr:3 00 \
+                &mova_t rs=%mova_rs esz=0 za=0
+MOVAZ_zt4       11000000 01 00011 0 v:1 .. 001100 za:1 off:1 zr:3 00 \
+                &mova_t rs=%mova_rs esz=1
+MOVAZ_zt4       11000000 10 00011 0 v:1 .. 001100 za:2 zr:3 00 \
+                &mova_t rs=%mova_rs esz=2 off=0
+MOVAZ_zt4       11000000 11 00011 0 v:1 .. 00110 za:3 zr:3 00 \
+                &mova_t rs=%mova_rs esz=3 off=0
+
 ### SME Move into/from ZT0
 
 MOVT_rzt        1100 0000 0100 1100 0 off:3 00 11111 rt:5