From: Richard Henderson <[email protected]>
Signed-off-by: Richard Henderson <[email protected]>
Message-id: [email protected]
Reviewed-by: Peter Maydell <[email protected]>
Signed-off-by: Peter Maydell <[email protected]>
---
target/arm/tcg/fp8_helper.c | 23 +++++++++++++++++++++++
target/arm/tcg/helper-fp8-defs.h | 2 ++
target/arm/tcg/sme.decode | 7 +++++++
target/arm/tcg/translate-sme.c | 10 ++++++++++
4 files changed, 42 insertions(+)
diff --git a/target/arm/tcg/fp8_helper.c b/target/arm/tcg/fp8_helper.c
index 08e04364fa..3c2d959099 100644
--- a/target/arm/tcg/fp8_helper.c
+++ b/target/arm/tcg/fp8_helper.c
@@ -892,3 +892,26 @@ void HELPER(sme_fmopa_sb)(void *vza, void *vzn, void *vzm,
void *vpn,
} while (row & 15);
}
}
+
+void HELPER(sme_fvdot_idx_sb)(void *vd, void *vn, void *vm,
+ CPUARMState *env, uint32_t desc)
+{
+ FP8MulContext ctx = fp8_mul_start(env, -1);
+ intptr_t oprsz = simd_maxsz(desc);
+ intptr_t elements = oprsz / sizeof(float32);
+ int idx_n = extract32(desc, SIMD_DATA_SHIFT, 2);
+ int idx_m = extract32(desc, SIMD_DATA_SHIFT + 2, 3);
+ float32 *d = vd;
+ uint8_t *n0 = vn;
+ uint8_t *n1 = vn + sizeof(ARMVectorReg);
+ uint16_t *m = vm;
+ intptr_t i = 0;
+
+ do {
+ uint16_t mm = m[H2(2 * i + idx_m)];
+ do {
+ uint16_t nn = n0[H1(4 * i + idx_n)] | (n1[H1(4 * i + idx_n)] << 8);
+ d[H4(i)] = f8dotadd_s(nn, mm, 2, d[H4(i)], &ctx);
+ } while (++i & 3);
+ } while (i < elements);
+}
diff --git a/target/arm/tcg/helper-fp8-defs.h b/target/arm/tcg/helper-fp8-defs.h
index 7c090ccad6..ef1375fea7 100644
--- a/target/arm/tcg/helper-fp8-defs.h
+++ b/target/arm/tcg/helper-fp8-defs.h
@@ -40,3 +40,5 @@ 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_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 7324ccddac..1de5f341ef 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -784,6 +784,13 @@ FMLALL_nx_b 11000001 0001 .... 1 .. 0.. ...10 00.. .
@azx_4x1_i4_o1
FDOT_nx_b 11000001 0101 .... 0 .. 0.. ....1 11 ... @azx_2x1_i2_o3
FDOT_nx_b 11000001 0101 .... 1 .. 0.. ...00 01 ... @azx_4x1_i2_o3
+%idx2_10_3 10:1 3:1
+@azx_4x2_i2_o3 ........ .... zm:4 . .. ... .... ... off:3 \
+ &azx_n n=4 rv=%mova_rv zn=%zn_ax2 idx=%idx2_10_3
+
+FVDOTB_sb 11000001 1101 .... 0 .. 01. ....0 0. ... @azx_4x2_i2_o3
+FVDOTT_sb 11000001 1101 .... 0 .. 01. ....0 1. ... @azx_4x2_i2_o3
+
### SME2 Add / Sub array accumulators
ADD_aaz_s 11000001 101 000000 .. 111 ....0 10 ... @az_2x2_o3
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index a9adaa02bd..a79b0a9b80 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1233,6 +1233,16 @@ static bool do_vdot(DisasContext *s, arg_azx_n *a,
gen_helper_gvec_4_ptr *fn)
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)
+static bool do_fvdot_sb(DisasContext *s, arg_azx_n *a, bool top)
+{
+ return do_azz_acc_fp8(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+ (2 * a->idx + top) << 2, 0, false,
+ gen_helper_sme_fvdot_idx_sb);
+}
+
+TRANS_FEAT(FVDOTB_sb, aa64_sme_f8f32, do_fvdot_sb, a, false)
+TRANS_FEAT(FVDOTT_sb, aa64_sme_f8f32, do_fvdot_sb, a, true)
+
static bool do_fmla(DisasContext *s, arg_azz_n *a, bool multi,
ARMFPStatusFlavour fpst, gen_helper_gvec_3_ptr *fn)
{
--
2.43.0
