Signed-off-by: Richard Henderson <[email protected]>
---
target/arm/cpu-features.h | 5 ++++
target/arm/tcg/helper-fp8-defs.h | 3 +++
target/arm/tcg/fp8_helper.c | 39 ++++++++++++++++++++++++++++++++
target/arm/tcg/translate-a64.c | 2 ++
target/arm/tcg/a64.decode | 2 ++
5 files changed, 51 insertions(+)
diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index 17d6acc14d..7bedc293fd 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -1610,6 +1610,11 @@ static inline bool isar_feature_aa64_f8dp4(const
ARMISARegisters *id)
return FIELD_EX64_IDREG(id, ID_AA64FPFR0, F8DP4);
}
+static inline bool isar_feature_aa64_f8dp2(const ARMISARegisters *id)
+{
+ return FIELD_EX64_IDREG(id, ID_AA64FPFR0, F8DP2);
+}
+
/*
* Combinations of feature tests, for ease of use with TRANS_FEAT.
*/
diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h
index ee6f2e9236..5995d77577 100644
--- a/target/arm/tcg/helper-fp8-defs.h
+++ b/target/arm/tcg/helper-fp8-defs.h
@@ -32,3 +32,6 @@ DEF_HELPER_FLAGS_5(gvec_fmla_idx_sb, TCG_CALL_NO_RWG, void,
ptr, ptr, ptr, env,
DEF_HELPER_FLAGS_5(gvec_fdot_sb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env,
i32)
DEF_HELPER_FLAGS_5(gvec_fdot_idx_sb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr,
env, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fdot_hb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env,
i32)
+DEF_HELPER_FLAGS_5(gvec_fdot_idx_hb, TCG_CALL_NO_RWG, void, ptr, ptr, ptr,
env, i32)
diff --git a/target/arm/tcg/fp8_helper.c b/target/arm/tcg/fp8_helper.c
index c9659eac35..d3bbea1735 100644
--- a/target/arm/tcg/fp8_helper.c
+++ b/target/arm/tcg/fp8_helper.c
@@ -768,3 +768,42 @@ void HELPER(gvec_fdot_idx_sb)(void *vd, void *vn, void *vm,
clear_tail(vd, oprsz, simd_maxsz(desc));
}
+
+void HELPER(gvec_fdot_hb)(void *vd, void *vn, void *vm,
+ CPUARMState *env, uint32_t desc)
+{
+ FP8MulContext ctx = fp8_mul_start(env, 0xf);
+ size_t oprsz = simd_oprsz(desc);
+ size_t nelem = oprsz / 2;
+ uint16_t *n = vn;
+ uint16_t *m = vm;
+ float16 *d = vd;
+
+ for (size_t i = 0; i < nelem; i++) {
+ d[i] = f8dotadd_h(n[i], m[i], 2, d[i], &ctx);
+ }
+
+ clear_tail(vd, oprsz, simd_maxsz(desc));
+}
+
+void HELPER(gvec_fdot_idx_hb)(void *vd, void *vn, void *vm,
+ CPUARMState *env, uint32_t desc)
+{
+ FP8MulContext ctx = fp8_mul_start(env, 0xf);
+ size_t idx = simd_data(desc);
+ size_t oprsz = simd_oprsz(desc);
+ size_t nelem = oprsz / 2;
+ uint16_t *n = vn;
+ uint16_t *m = vm;
+ float16 *d = vd;
+ size_t i = 0;
+
+ do {
+ uint16_t e1 = m[i + H2(idx)];
+ do {
+ d[i] = f8dotadd_h(n[i], e1, 2, d[i], &ctx);
+ } while (++i % 8 != 0);
+ } while (i < nelem);
+
+ clear_tail(vd, oprsz, simd_maxsz(desc));
+}
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 8ea63e94fe..c5ea6b27a9 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -7417,6 +7417,7 @@ static bool do_f8dot(DisasContext *s, arg_qrrr_e *a,
}
TRANS_FEAT(FDOT_sb_v, aa64_f8dp4, do_f8dot, a, gen_helper_gvec_fdot_sb)
+TRANS_FEAT(FDOT_hb_v, aa64_f8dp2, do_f8dot, a, gen_helper_gvec_fdot_hb)
static bool do_f8dot_idx(DisasContext *s, arg_qrrx_e *a,
gen_helper_gvec_3_ptr *fn)
@@ -7432,6 +7433,7 @@ static bool do_f8dot_idx(DisasContext *s, arg_qrrx_e *a,
}
TRANS_FEAT(FDOT_sb_vi, aa64_f8dp4, do_f8dot_idx, a,
gen_helper_gvec_fdot_idx_sb)
+TRANS_FEAT(FDOT_hb_vi, aa64_f8dp2, do_f8dot_idx, a,
gen_helper_gvec_fdot_idx_hb)
static bool do_int3_vector_idx(DisasContext *s, arg_qrrx_e *a,
gen_helper_gvec_3 * const fns[2])
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index d78a3d5486..d1254355b6 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -1214,6 +1214,7 @@ FMLALL_sb_v 0.00 1110 0.0 rm:5 110001 rn:5 rd:5 \
&rxx idxm=0 idxn=%fmlall_idxn
FDOT_sb_v 0.00 1110 000 ..... 11111 1 ..... ..... @qrrr_s
+FDOT_hb_v 0.00 1110 010 ..... 11111 1 ..... ..... @qrrr_h
### Advanced SIMD scalar x indexed element
@@ -1340,6 +1341,7 @@ FMLALL_sb_vi 0 . 10 1111 0 . ... rm:3 1000 . 0 rn:5
rd:5 \
&rxx idxm=%hlm4 idxn=%fmlall_idxn
FDOT_sb_vi 0.00 1111 00 . ..... 0000 . 0 ..... ..... @qrrx_s
+FDOT_hb_vi 0.00 1111 01 .. .... 0000 . 0 ..... ..... @qrrx_h
# Floating-point conditional select
--
2.43.0
