target/arm: Implement SME2 FVDOT, BFVDOT

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-40-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index ec93ff57ff3a45eaa9513a0e2d47d08553c2188b..8f5a1b3c9082efaa3ca29f9fb4f55acc6d6c88e4 100644 (file)
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -178,3 +178,5 @@ DEF_HELPER_FLAGS_6(sme2_fdot_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_6(sme2_fvdot_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, env, i32)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index a05b63380cb1a2f3bc7d2196d3a1a79da2c8294a..d8d389af2b9c71a0f87209bf80572d47c623159b 100644 (file)
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -1089,6 +1089,8 @@ DEF_HELPER_FLAGS_6(gvec_bfdot, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_FLAGS_6(gvec_bfdot_idx, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_6(sme2_bfvdot_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, env, i32)
 
 DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, env, i32)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 18e625605fb1c5fc9b461fc240f73497447f15c4..7c057bcad2021355a1dcbc9b94b7b5280ad246cd 100644 (file)
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -374,3 +374,6 @@ FDOT_nx         11000001 0101 .... 1 .. 1 .. ...00 01 ...   @azx_4x1_i2_o3
 
 BFDOT_nx        11000001 0101 .... 0 .. 1 .. ....0 11 ...   @azx_2x1_i2_o3
 BFDOT_nx        11000001 0101 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_i2_o3
+
+FVDOT           11000001 0101 .... 0 .. 0 .. ....0 01 ...   @azx_2x1_i2_o3
+BFVDOT          11000001 0101 .... 0 .. 0 .. ....0 11 ...   @azx_2x1_i2_o3

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 60322be3d0b4f46de15fc50df10cd21e95f56628..8b4586546126fcf992654bf196519f7ed0d9d106 100644 (file)
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1196,6 +1196,36 @@ void HELPER(sme2_fdot_idx_h)(void *vd, void *vn, void *vm, void *va,
     }
 }
 
+void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va,
+                              CPUARMState *env, uint32_t desc)
+{
+    intptr_t i, j, oprsz = simd_maxsz(desc);
+    intptr_t elements = oprsz / sizeof(float32);
+    intptr_t eltspersegment = MIN(4, elements);
+    int idx = extract32(desc, SIMD_DATA_SHIFT, 2);
+    int sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+    float_status fpst_odd, *fpst_std, *fpst_f16;
+    float32 *d = vd, *a = va;
+    uint16_t *n0 = vn;
+    uint16_t *n1 = vn + sizeof(ARMVectorReg);
+    uint32_t *m = (uint32_t *)vm + H4(idx);
+
+    fpst_std = &env->vfp.fp_status[FPST_ZA];
+    fpst_f16 = &env->vfp.fp_status[FPST_ZA_F16];
+    fpst_odd = *fpst_std;
+    set_float_rounding_mode(float_round_to_odd, &fpst_odd);
+
+    for (i = 0; i < elements; i += eltspersegment) {
+        uint32_t mm = m[i];
+        for (j = 0; j < eltspersegment; ++j) {
+            uint32_t nn = (n0[H2(2 * (i + j) + sel)])
+                        | (n1[H2(2 * (i + j) + sel)] << 16);
+            d[i + H4(j)] = f16_dotadd(a[i + H4(j)], nn, mm,
+                                      fpst_f16, fpst_std, &fpst_odd);
+        }
+    }
+}
+
 void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm,
                         void *vpn, void *vpm, CPUARMState *env, uint32_t desc)
 {

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 965a49465e40ba723a90c3800689d7d4c1db4400..410a8d037c0649dda1572baf0d519cbd3201b0ee 100644 (file)
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -938,3 +938,27 @@ static bool do_bfdot_nx(DisasContext *s, arg_azx_n *a)
 }
 
 TRANS_FEAT(BFDOT_nx, aa64_sme2, do_bfdot_nx, a)
+
+static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
+{
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / 2;
+        TCGv_ptr t_za = get_zarray(s, a->rv, a->off, 2, 1);
+        TCGv_ptr t_zn = vec_full_reg_ptr(s, a->zn);
+        TCGv_ptr t_zm = vec_full_reg_ptr(s, a->zm);
+        TCGv_ptr t = tcg_temp_new_ptr();
+
+        for (int i = 0; i < 2; ++i) {
+            int o_za = i * vstride * sizeof(ARMVectorReg);
+            int desc = simd_desc(svl, svl, a->idx | (i << 2));
+
+            tcg_gen_addi_ptr(t, t_za, o_za);
+            fn(t, t_zn, t_zm, t, tcg_env, tcg_constant_i32(desc));
+        }
+    }
+    return true;
+}
+
+TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
+TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)

diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 5dcd6f9282d5a4c1ba75cb821495a0f4d9f8fb37..616f4050e47a88a4f006f65850898d6080038d4d 100644 (file)
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -3110,6 +3110,45 @@ void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm,
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
 
+void HELPER(sme2_bfvdot_idx)(void *vd, void *vn, void *vm,
+                             void *va, CPUARMState *env, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT, 2);
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+    intptr_t elements = opr_sz / 4;
+    intptr_t eltspersegment = MIN(16 / 4, elements);
+    float32 *d = vd, *a = va;
+    uint16_t *n0 = vn;
+    uint16_t *n1 = vn + sizeof(ARMVectorReg);
+    uint32_t *m = vm;
+    float_status fpst, fpst_odd;
+
+    if (is_ebf(env, &fpst, &fpst_odd)) {
+        for (i = 0; i < elements; i += eltspersegment) {
+            uint32_t m_idx = m[i + H4(idx)];
+
+            for (j = 0; j < eltspersegment; j++) {
+                uint32_t nn = (n0[H2(2 * (i + j) + sel)])
+                            | (n1[H2(2 * (i + j) + sel)] << 16);
+                d[i + H4(j)] = bfdotadd_ebf(a[i + H4(j)], nn, m_idx,
+                                            &fpst, &fpst_odd);
+            }
+        }
+    } else {
+        for (i = 0; i < elements; i += eltspersegment) {
+            uint32_t m_idx = m[i + H4(idx)];
+
+            for (j = 0; j < eltspersegment; j++) {
+                uint32_t nn = (n0[H2(2 * (i + j) + sel)])
+                            | (n1[H2(2 * (i + j) + sel)] << 16);
+                d[i + H4(j)] = bfdotadd(a[i + H4(j)], nn, m_idx, &fpst);
+            }
+        }
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
 void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va,
                          CPUARMState *env, uint32_t desc)
 {