Signed-off-by: Richard Henderson <[email protected]>
---
target/arm/tcg/helper-sve-defs.h | 3 +++
target/arm/tcg/translate-sve.c | 5 +++++
target/arm/tcg/vec_helper64.c | 30 ++++++++++++++++++++++++++++++
target/arm/tcg/sve.decode | 5 +++++
4 files changed, 43 insertions(+)
diff --git a/target/arm/tcg/helper-sve-defs.h b/target/arm/tcg/helper-sve-defs.h
index f78e77662d..498468a772 100644
--- a/target/arm/tcg/helper-sve-defs.h
+++ b/target/arm/tcg/helper-sve-defs.h
@@ -3215,3 +3215,6 @@ DEF_HELPER_FLAGS_4(sve_expand_b, TCG_CALL_NO_WG, void,
ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_expand_h, TCG_CALL_NO_WG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_expand_s, TCG_CALL_NO_WG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_expand_d, TCG_CALL_NO_WG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_pmull_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_pmlal_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 14378cf066..b7849b5be5 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -8341,6 +8341,11 @@ TRANS_FEAT_STREAMING_IF(AESEMC, aa64_sve_aes2,
aa64_ssve_aes,
TRANS_FEAT_STREAMING_IF(AESDIMC, aa64_sve_aes2, aa64_ssve_aes,
do_aes2_idx, a, gen_helper_crypto_aesdimc)
+TRANS_FEAT_STREAMING_IF(PMULL, aa64_sve_aes2, aa64_ssve_aes,
+ gen_gvec_ool_arg_zzz, gen_helper_sve_pmull_q, a, 0)
+TRANS_FEAT_STREAMING_IF(PMLAL, aa64_sve_aes2, aa64_ssve_aes,
+ gen_gvec_ool_arg_zzz, gen_helper_sve_pmlal_q, a, 0)
+
TRANS_FEAT(FCVTNT_sh_m, aa64_sme_or_sve2, gen_gvec_fpst_arg_zpz,
gen_helper_sve2_fcvtnt_sh, a, 0, FPST_A64)
TRANS_FEAT(FCVTNT_sh_z, aa64_sme2p2_or_sve2p2, gen_gvec_fpst_arg_zpz,
diff --git a/target/arm/tcg/vec_helper64.c b/target/arm/tcg/vec_helper64.c
index 8879969350..7d4e21b9c7 100644
--- a/target/arm/tcg/vec_helper64.c
+++ b/target/arm/tcg/vec_helper64.c
@@ -89,6 +89,36 @@ void HELPER(sve2_pmull_d)(void *vd, void *vn, void *vm,
uint32_t desc)
}
}
+void HELPER(sve_pmull_q)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t opr_sz = simd_oprsz(desc);
+ uint64_t *n = vn, *m = vm;
+ Int128 *d0 = vd;
+ Int128 *d1 = vd + sizeof(ARMVectorReg);
+
+ for (intptr_t i = 0; i < opr_sz / 16; ++i) {
+ Int128 rl = clmul_64(n[2 * i + 0], m[2 * i + 0]);
+ Int128 rh = clmul_64(n[2 * i + 1], m[2 * i + 1]);
+ d0[i] = rl;
+ d1[i] = rh;
+ }
+}
+
+void HELPER(sve_pmlal_q)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t opr_sz = simd_oprsz(desc);
+ uint64_t *n = vn, *m = vm;
+ Int128 *d0 = vd;
+ Int128 *d1 = vd + sizeof(ARMVectorReg);
+
+ for (intptr_t i = 0; i < opr_sz / 16; ++i) {
+ Int128 rl = clmul_64(n[2 * i + 0], m[2 * i + 0]);
+ Int128 rh = clmul_64(n[2 * i + 1], m[2 * i + 1]);
+ d0[i] = int128_xor(d0[i], rl);
+ d1[i] = int128_xor(d1[i], rh);
+ }
+}
+
DO_3OP_PAIR(gvec_ah_fmaxp_h, helper_vfp_ah_maxh, float16, H2)
DO_3OP_PAIR(gvec_ah_fmaxp_s, helper_vfp_ah_maxs, float32, H4)
DO_3OP_PAIR(gvec_ah_fmaxp_d, helper_vfp_ah_maxd, float64, /**/)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 7030d81db7..42f451ff9f 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1994,6 +1994,11 @@ AESEMC 01000101 00 1 .. .11111010 ..... ...00
@aes2_4
AESDIMC 01000101 00 1 .. .11111011 ..... ....0 @aes2_2
AESDIMC 01000101 00 1 .. .11111011 ..... ...00 @aes2_4
+PMULL 01000101 00 1 rm:5 111110 rn:5 ....0 \
+ &rrr_esz esz=0 rd=%zd_ax2
+PMLAL 01000101 00 1 rm:5 111111 rn:5 ....0 \
+ &rrr_esz esz=0 rd=%zd_ax2
+
# SVE2 crypto constructive binary operations
SM4EKEY 01000101 00 1 ..... 11110 0 ..... ..... @rd_rn_rm_e0
RAX1 01000101 00 1 ..... 11110 1 ..... ..... @rd_rn_rm_e0
--
2.43.0
