From: Richard Henderson <[email protected]>
Signed-off-by: Richard Henderson <[email protected]>
Reviewed-by: Peter Maydell <[email protected]>
Message-id: [email protected]
Signed-off-by: Peter Maydell <[email protected]>
---
target/arm/cpu-features.h | 5 +++++
target/arm/tcg/fp8_helper.c | 35 ++++++++++++++++++++++++++++++++
target/arm/tcg/helper-fp8-defs.h | 2 ++
target/arm/tcg/sme.decode | 2 ++
target/arm/tcg/translate-sme.c | 19 +++++++++++++++++
5 files changed, 63 insertions(+)
diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index c07bcb0a73..45213f71ab 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -1600,6 +1600,11 @@ static inline bool isar_feature_aa64_sme_b16b16(const
ARMISARegisters *id)
return FIELD_EX64_IDREG(id, ID_AA64SMFR0, B16B16);
}
+static inline bool isar_feature_aa64_sme_f8f32(const ARMISARegisters *id)
+{
+ return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F8F32);
+}
+
static inline bool isar_feature_aa64_sme_f16f16(const ARMISARegisters *id)
{
return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F16F16);
diff --git a/target/arm/tcg/fp8_helper.c b/target/arm/tcg/fp8_helper.c
index bd0877071b..08e04364fa 100644
--- a/target/arm/tcg/fp8_helper.c
+++ b/target/arm/tcg/fp8_helper.c
@@ -857,3 +857,38 @@ void HELPER(gvec_fmmla_hb)(void *vd, void *vn, void *vm,
clear_tail(vd, oprsz, simd_maxsz(desc));
}
+
+void HELPER(sme_fmopa_sb)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
+{
+ FP8MulContext ctx = fp8_mul_start(env, -1);
+ 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);
+ uint32_t n = *(uint32_t *)(vzn + H1_4(row));
+
+ n &= expand_pred_b(prow & 0xf);
+
+ for (intptr_t col = 0; col < oprsz; ) {
+ uint16_t pcol = pm[H2(col >> 4)];
+ do {
+ if (prow & pcol & 0xf) {
+ uint32_t *a = vza_row + H1_4(col);
+ uint32_t m = *(uint32_t *)(vzm + H1_4(col));
+
+ m &= expand_pred_b(pcol & 0xf);
+ *a = f8dotadd_s(n, m, 4, *a, &ctx);
+ }
+ col += 4;
+ pcol >>= 4;
+ } while (col & 15);
+ }
+ row += 4;
+ prow >>= 4;
+ } while (row & 15);
+ }
+}
diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h
index e942308af4..7c090ccad6 100644
--- a/target/arm/tcg/helper-fp8-defs.h
+++ b/target/arm/tcg/helper-fp8-defs.h
@@ -38,3 +38,5 @@ DEF_HELPER_FLAGS_5(gvec_fdot_idx_hb, TCG_CALL_NO_RWG, void,
ptr, ptr, ptr, env,
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)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 495330aed7..e668293efd 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -198,6 +198,8 @@ BFMOPA 10000001 101 ..... ... ... ..... . 100 .
@op_16
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
+
SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32
SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32
USMOPA_s 1010000 1 10 0 ..... ... ... ..... . 00 .. @op_32
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 98d3d18791..63c6e2c9b1 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -616,6 +616,25 @@ 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)
+{
+ 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));
+ }
+ return true;
+}
+
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)
--
2.43.0
