target/arm: Implement SME2 BFMOPA (non-widening)

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-106-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 fac70a82b92ec0f560ce5d8a9692c280cf471cbb..1fc756bec6e552a9654b8012b6436005b63a6261 100644 (file)
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -145,6 +145,8 @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
@@ -156,6 +158,8 @@ DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_bfmops, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
@@ -167,6 +171,8 @@ DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_7(sme_ah_bfmops_w, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_ah_bfmops, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 3c58fdd2a0e9266a4782e365b1d28596a748a1a8..6bb9aa2a90e806a2d236eec29f0e9e4fd641b6d7 100644 (file)
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -191,6 +191,8 @@ FMOPA_h         10000001 100 ..... ... ... ..... . 100 .        @op_16
 FMOPA_s         10000000 100 ..... ... ... ..... . 00 ..        @op_32
 FMOPA_d         10000000 110 ..... ... ... ..... . 0 ...        @op_64
 
+BFMOPA          10000001 101 ..... ... ... ..... . 100 .        @op_16
+
 BFMOPA_w        10000001 100 ..... ... ... ..... . 00 ..        @op_32
 FMOPA_w_h       10000001 101 ..... ... ... ..... . 00 ..        @op_32
 

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index d23d9f08d2985cb26e5b5950c60c75e8587af788..bb8ed1ed0e2f3f9bad2b4f1af083e604e976f14a 100644 (file)
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1144,6 +1144,57 @@ void HELPER(sme_ah_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn,
                float_muladd_negate_product);
 }
 
+static void do_bfmopa(void *vza, void *vzn, void *vzm, uint16_t *pn,
+                      uint16_t *pm, float_status *fpst, uint32_t desc,
+                      uint16_t negx, int negf)
+{
+    intptr_t row, col, oprsz = simd_maxsz(desc);
+
+    for (row = 0; row < oprsz; ) {
+        uint16_t pa = pn[H2(row >> 4)];
+        do {
+            if (pa & 1) {
+                void *vza_row = vza + tile_vslice_offset(row);
+                uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx;
+
+                for (col = 0; col < oprsz; ) {
+                    uint16_t pb = pm[H2(col >> 4)];
+                    do {
+                        if (pb & 1) {
+                            uint16_t *a = vza_row + H1_2(col);
+                            uint16_t *m = vzm + H1_2(col);
+                            *a = bfloat16_muladd(n, *m, *a, negf, fpst);
+                        }
+                        col += 2;
+                        pb >>= 2;
+                    } while (col & 15);
+                }
+            }
+            row += 2;
+            pa >>= 2;
+        } while (row & 15);
+    }
+}
+
+void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn,
+                        void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0);
+}
+
+void HELPER(sme_bfmops)(void *vza, void *vzn, void *vzm, void *vpn,
+                        void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0);
+}
+
+void HELPER(sme_ah_bfmops)(void *vza, void *vzn, void *vzm, void *vpn,
+                           void *vpm, float_status *fpst, uint32_t desc)
+{
+    do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0,
+              float_muladd_negate_product);
+}
+
 /*
  * Alter PAIR as needed for controlling predicates being false,
  * and for NEG on an enabled row element.

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 119a5665e67c12c11106b00058e88d3f74b202d7..65fc8bc9b2ff588efab7cad64c80f073bfd73dfc 100644 (file)
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -582,6 +582,11 @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, FPST_ZA,
            : !s->fpcr_ah ? gen_helper_sme_fmops_d
            : gen_helper_sme_ah_fmops_d)
 
+TRANS_FEAT(BFMOPA, aa64_sme_b16b16, do_outprod_fpst, a, MO_16, FPST_ZA,
+           !a->sub ? gen_helper_sme_bfmopa
+           : !s->fpcr_ah ? gen_helper_sme_bfmops
+           : gen_helper_sme_ah_bfmops)
+
 TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32,
            !a->sub ? gen_helper_sme_bfmopa_w
            : !s->fpcr_ah ? gen_helper_sme_bfmops_w