target/arm: Implement FMOPA (widening, 2-way, FP8 to FP16)

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260625015159.719300-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/fp8_helper.c b/target/arm/tcg/fp8_helper.c
index 3c2d95909936bba80a55477ce3590d3e610d29f3..5606f0fd8e106c998bc4aeef2be194abcbead2a8 100644 (file)
--- a/target/arm/tcg/fp8_helper.c
+++ b/target/arm/tcg/fp8_helper.c
@@ -893,6 +893,41 @@ void HELPER(sme_fmopa_sb)(void *vza, void *vzn, void *vzm, void *vpn,
     }
 }
 
+void HELPER(sme_fmopa_hb)(void *vza, void *vzn, void *vzm, void *vpn,
+                          void *vpm, CPUARMState *env, uint32_t desc)
+{
+    FP8MulContext ctx = fp8_mul_start(env, 0xf);
+    intptr_t oprsz = simd_maxsz(desc);
+    uint16_t *pn = vpn, *pm = vpm;
+
+    for (intptr_t row = 0; row < oprsz; ) {
+        uint16_t prow = pn[H2(row >> 4)];
+        do {
+            void *vza_row = vza + tile_vslice_offset(row);
+            uint16_t n = *(uint16_t *)(vzn + H1_2(row));
+
+            n &= expand_pred_b(prow & 3);
+
+            for (intptr_t col = 0; col < oprsz; ) {
+                uint16_t pcol = pm[H2(col >> 4)];
+                do {
+                    if (prow & pcol & 0x3) {
+                        uint16_t *a = vza_row + H1_2(col);
+                        uint16_t m = *(uint16_t *)(vzm + H1_2(col));
+
+                        m &= expand_pred_b(pcol & 3);
+                        *a = f8dotadd_h(n, m, 2, *a, &ctx);
+                    }
+                    col += 2;
+                    pcol >>= 2;
+                } while (col & 15);
+            }
+            row += 2;
+            prow >>= 2;
+        } while (row & 15);
+    }
+}
+
 void HELPER(sme_fvdot_idx_sb)(void *vd, void *vn, void *vm,
                               CPUARMState *env, uint32_t desc)
 {

diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h
index ef1375fea7b5f3a0bb4f7b803efb29be062539e4..05bf8dbdc259c5e315de84e30fc866dfb5add9c9 100644 (file)
--- a/target/arm/tcg/helper-fp8-defs.h
+++ b/target/arm/tcg/helper-fp8-defs.h
@@ -40,5 +40,6 @@ DEF_HELPER_FLAGS_5(gvec_fmmla_sb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32
 DEF_HELPER_FLAGS_5(gvec_fmmla_hb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32)
 
 DEF_HELPER_FLAGS_7(sme_fmopa_sb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_fmopa_hb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32)
 
 DEF_HELPER_FLAGS_5(sme_fvdot_idx_sb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 1dd3b7c8b21e698b36e79030c5b363dfbd59179f..755d5f00d086a5302a846aea9c6554bc64e15ae1 100644 (file)
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -199,6 +199,7 @@ BFMOPA_w        10000001 100 ..... ... ... ..... . 00 ..        @op_32
 FMOPA_w_h       10000001 101 ..... ... ... ..... . 00 ..        @op_32
 
 FMOPA_sb        10000000 101 zm:5 pm:3 pn:3 zn:5 0 00 zad:2     &op sub=0
+FMOPA_hb        10000000 101 zm:5 pm:3 pn:3 zn:5 0100 zad:1     &op sub=0
 
 SMOPA_s         1010000 0 10 0 ..... ... ... ..... . 00 ..      @op_32
 SUMOPA_s        1010000 0 10 1 ..... ... ... ..... . 00 ..      @op_32

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 197274d00e4c06a1963c6ea76d60890cd1fd938b..7eeac2848055e5d869aef8b5cda2dc03f0317f1d 100644 (file)
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -616,25 +616,29 @@ TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32,
            : !s->fpcr_ah ? gen_helper_sme_bfmops_w
            : gen_helper_sme_ah_bfmops_w)
 
-static bool trans_FMOPA_sb(DisasContext *s, arg_op *a)
+static bool do_outprod_fp8(DisasContext *s, arg_op *a, MemOp esz,
+                           gen_helper_gvec_5_ptr *fn)
 {
-    if (!dc_isar_feature(aa64_sme_f8f32, s)) {
-        return false;
-    }
     if (fpmr_access_check(s) && sme_smza_enabled_check(s)) {
         int svl = streaming_vec_reg_size(s);
         uint32_t desc = simd_desc(svl, svl, 0);
 
-        gen_helper_sme_fmopa_sb(get_tile(s, MO_32, a->zad),
-                                vec_full_reg_ptr(s, a->zn),
-                                vec_full_reg_ptr(s, a->zm),
-                                pred_full_reg_ptr(s, a->pn),
-                                pred_full_reg_ptr(s, a->pm),
-                                tcg_env, tcg_constant_i32(desc));
+        TCGv_ptr za = get_tile(s, esz, a->zad);
+        TCGv_ptr zn = vec_full_reg_ptr(s, a->zn);
+        TCGv_ptr zm = vec_full_reg_ptr(s, a->zm);
+        TCGv_ptr pn = pred_full_reg_ptr(s, a->pn);
+        TCGv_ptr pm = pred_full_reg_ptr(s, a->pm);
+
+        fn(za, zn, zm, pn, pm, tcg_env, tcg_constant_i32(desc));
     }
     return true;
 }
 
+TRANS_FEAT(FMOPA_sb, aa64_sme_f8f32, do_outprod_fp8,
+           a, MO_32, gen_helper_sme_fmopa_sb)
+TRANS_FEAT(FMOPA_hb, aa64_sme_f8f16, do_outprod_fp8,
+           a, MO_16, gen_helper_sme_fmopa_hb)
+
 TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s)
 TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s)
 TRANS_FEAT(SUMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_sumopa_s)