Exclude PMULL from this category for the moment. Signed-off-by: Richard Henderson <richard.hender...@linaro.org> --- target/arm/helper-sve.h | 15 +++++++++++++++ target/arm/sve.decode | 9 +++++++++ target/arm/sve_helper.c | 31 +++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 9 +++++++++ 4 files changed, 64 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 6a95c6085c..c4784919d2 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -2355,4 +2355,19 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd_mte, TCG_CALL_NO_WG, DEF_HELPER_FLAGS_6(sve_stdd_be_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_smull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_umull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 9994e1eb71..2410dd85a1 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -1199,3 +1199,12 @@ SSUBWB 01000101 .. 0 ..... 010 100 ..... ..... @rd_rn_rm SSUBWT 01000101 .. 0 ..... 010 101 ..... ..... @rd_rn_rm USUBWB 01000101 .. 0 ..... 010 110 ..... ..... @rd_rn_rm USUBWT 01000101 .. 0 ..... 010 111 ..... ..... @rd_rn_rm + +## SVE2 integer multiply long + +SQDMULLB_zzz 01000101 .. 0 ..... 011 000 ..... ..... @rd_rn_rm +SQDMULLT_zzz 01000101 .. 0 ..... 011 001 ..... ..... @rd_rn_rm +SMULLB_zzz 01000101 .. 0 ..... 011 100 ..... ..... @rd_rn_rm +SMULLT_zzz 01000101 .. 0 ..... 011 101 ..... ..... @rd_rn_rm +UMULLB_zzz 01000101 .. 0 ..... 011 110 ..... ..... @rd_rn_rm +UMULLT_zzz 01000101 .. 0 ..... 011 111 ..... ..... @rd_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index 44503626e4..130697f3d9 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -1129,6 +1129,37 @@ DO_ZZZ_TB(sve2_uabdl_h, uint16_t, uint8_t, DO_ABD) DO_ZZZ_TB(sve2_uabdl_s, uint32_t, uint16_t, DO_ABD) DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t, DO_ABD) +DO_ZZZ_TB(sve2_smull_zzz_h, int16_t, int8_t, DO_MUL) +DO_ZZZ_TB(sve2_smull_zzz_s, int32_t, int16_t, DO_MUL) +DO_ZZZ_TB(sve2_smull_zzz_d, int64_t, int32_t, DO_MUL) + +DO_ZZZ_TB(sve2_umull_zzz_h, uint16_t, uint8_t, DO_MUL) +DO_ZZZ_TB(sve2_umull_zzz_s, uint32_t, uint16_t, DO_MUL) +DO_ZZZ_TB(sve2_umull_zzz_d, uint64_t, uint32_t, DO_MUL) + +/* Note that the multiply cannot overflow, but the doubling can. */ +static inline int16_t do_sqdmull_h(int16_t n, int16_t m) +{ + int16_t val = n * m; + return DO_SQADD_H(val, val); +} + +static inline int32_t do_sqdmull_s(int32_t n, int32_t m) +{ + int32_t val = n * m; + return DO_SQADD_S(val, val); +} + +static inline int64_t do_sqdmull_d(int64_t n, int64_t m) +{ + int64_t val = n * m; + return do_sqadd_d(val, val); +} + +DO_ZZZ_TB(sve2_sqdmull_zzz_h, int16_t, int8_t, do_sqdmull_h) +DO_ZZZ_TB(sve2_sqdmull_zzz_s, int32_t, int16_t, do_sqdmull_s) +DO_ZZZ_TB(sve2_sqdmull_zzz_d, int64_t, int32_t, do_sqdmull_d) + #undef DO_ZZZ_TB #define DO_ZZZ_WTB(NAME, TYPE, TYPEN, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index fb214360bf..c66ec9eb83 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -6055,6 +6055,15 @@ DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true) DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true) DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true) +DO_SVE2_ZZZ_TB(SQDMULLB_zzz, sqdmull_zzz, false, false) +DO_SVE2_ZZZ_TB(SQDMULLT_zzz, sqdmull_zzz, true, true) + +DO_SVE2_ZZZ_TB(SMULLB_zzz, smull_zzz, false, false) +DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true) + +DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false) +DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true) + #define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \ static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ { \ -- 2.20.1