@@ -312,3 +312,27 @@ DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i3
DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
@@ -334,4 +334,19 @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah)
bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst);
bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
+static inline uint64_t extractn(uint64_t *p, unsigned pos, unsigned len)
+{
+ uint64_t x;
+
+ p += pos / 64;
+ pos = pos % 64;
+
+ x = p[0];
+ if (pos + len > 64) {
+ x = (x >> pos) | (p[1] << (-pos & 63));
+ pos = 0;
+ }
+ return extract64(x, pos, len);
+}
+
#endif /* TARGET_ARM_VEC_INTERNAL_H */
@@ -2020,3 +2020,62 @@ FCLAMP(sme2_fclamp_d, float64, H8)
FCLAMP(sme2_bfclamp, bfloat16, H2)
#undef FCLAMP
+
+#define DO_LUT_PRIM(SUFF, TYPE, H) \
+static inline void do_lut_##SUFF \
+ (void *zd, uint64_t *indexes, uint32_t *zt0, unsigned elements, \
+ unsigned segment, unsigned dstride, unsigned isize, unsigned nreg) \
+{ \
+ for (unsigned r = 0; r < nreg; ++r) { \
+ TYPE *dst = zd + dstride * r; \
+ unsigned base = (segment + r) * elements; \
+ for (unsigned e = 0; e < elements; ++e) { \
+ unsigned index = extractn(indexes, base + e * isize, isize); \
+ dst[H(e)] = zt0[H4(index)]; \
+ } \
+ } \
+}
+
+DO_LUT_PRIM(b, uint8_t, H1)
+DO_LUT_PRIM(h, uint16_t, H2)
+DO_LUT_PRIM(s, uint32_t, H4)
+
+#define DO_LUT(ISIZE, NREG, SUFF, TYPE) \
+void helper_sme2_luti##ISIZE##_##NREG##SUFF \
+ (void *zd, void *zn, CPUARMState *env, uint32_t desc) \
+{ \
+ unsigned vl = simd_oprsz(desc); \
+ unsigned strided = extract32(desc, SIMD_DATA_SHIFT, 1); \
+ unsigned idx = extract32(desc, SIMD_DATA_SHIFT + 1, 4); \
+ unsigned dstride = (!strided ? 1 : NREG == 4 ? 4 : 8); \
+ unsigned segments = sizeof(TYPE) / (ISIZE * NREG); \
+ unsigned segment = idx & (segments - 1); \
+ ARMVectorReg indexes; \
+ memcpy(&indexes, zn, vl); \
+ do_lut_##SUFF(zd, indexes.d, (uint32_t *)&env->za_state.zt0, \
+ vl / sizeof(TYPE), segment * NREG, \
+ dstride * sizeof(ARMVectorReg), ISIZE, NREG); \
+}
+
+DO_LUT(2,1,b, uint8_t)
+DO_LUT(2,1,h, uint16_t)
+DO_LUT(2,1,s, uint32_t)
+DO_LUT(2,2,b, uint8_t)
+DO_LUT(2,2,h, uint16_t)
+DO_LUT(2,2,s, uint32_t)
+DO_LUT(2,4,b, uint8_t)
+DO_LUT(2,4,h, uint16_t)
+DO_LUT(2,4,s, uint32_t)
+
+DO_LUT(4,1,b, uint8_t)
+DO_LUT(4,1,h, uint16_t)
+DO_LUT(4,1,s, uint32_t)
+DO_LUT(4,2,b, uint8_t)
+DO_LUT(4,2,h, uint16_t)
+DO_LUT(4,2,s, uint32_t)
+DO_LUT(4,4,b, uint8_t)
+DO_LUT(4,4,h, uint16_t)
+DO_LUT(4,4,s, uint32_t)
+
+#undef DO_LUT
+#undef DO_LUT_PRIM
@@ -3035,21 +3035,6 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc)
}
}
-static uint64_t extractn(uint64_t *p, unsigned pos, unsigned len)
-{
- uint64_t x;
-
- p += pos / 64;
- pos = pos % 64;
-
- x = p[0];
- if (pos + len > 64) {
- x = (x >> pos) | (p[1] << (-pos & 63));
- pos = 0;
- }
- return extract64(x, pos, len);
-}
-
static void depositn(uint64_t *p, unsigned pos, unsigned len, uint64_t val)
{
p += pos / 64;
@@ -1586,3 +1586,59 @@ static bool trans_SEL(DisasContext *s, arg_SEL *a)
}
return true;
}
+
+static bool do_lut(DisasContext *s, arg_lut *a,
+ gen_helper_gvec_2_ptr *fn, int data)
+{
+ if (sme_sm_enabled_check(s) && sme2_zt0_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd),
+ vec_full_reg_offset(s, a->zn),
+ tcg_env, svl, svl, data, fn);
+ }
+ return true;
+}
+
+TRANS_FEAT(LUTI2_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1b, 0)
+TRANS_FEAT(LUTI2_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1h, 0)
+TRANS_FEAT(LUTI2_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1s, 0)
+
+TRANS_FEAT(LUTI2_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2b, 1)
+TRANS_FEAT(LUTI2_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2h, 1)
+TRANS_FEAT(LUTI2_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2s, 1)
+
+TRANS_FEAT(LUTI2_c_4b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4b, 1)
+TRANS_FEAT(LUTI2_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4h, 1)
+TRANS_FEAT(LUTI2_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4s, 1)
+
+TRANS_FEAT(LUTI4_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1b, 0)
+TRANS_FEAT(LUTI4_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1h, 0)
+TRANS_FEAT(LUTI4_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1s, 0)
+
+TRANS_FEAT(LUTI4_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2b, 1)
+TRANS_FEAT(LUTI4_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2h, 1)
+TRANS_FEAT(LUTI4_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2s, 1)
+
+TRANS_FEAT(LUTI4_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4h, 1)
+TRANS_FEAT(LUTI4_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4s, 1)
+
+static bool do_lut_s4(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+ return !(a->zd & 0b01100) && do_lut(s, a, fn, 4);
+}
+
+static bool do_lut_s8(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+ return !(a->zd & 0b01000) && do_lut(s, a, fn, 8);
+}
+
+TRANS_FEAT(LUTI2_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2b)
+TRANS_FEAT(LUTI2_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2h)
+
+TRANS_FEAT(LUTI2_s_4b, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4b)
+TRANS_FEAT(LUTI2_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4h)
+
+TRANS_FEAT(LUTI4_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2b)
+TRANS_FEAT(LUTI4_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2h)
+
+TRANS_FEAT(LUTI4_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti4_4h)
@@ -908,3 +908,45 @@ ZERO_za 11000000 000011 110 .. 0000000000 00. \
&zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
ZERO_za 11000000 000011 111 .. 0000000000 00. \
&zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4
+
+### SME Lookup Table Read
+
+&lut zd zn idx
+
+# LUTI2, consecutive
+LUTI2_c_1b 1100 0000 1100 11 idx:4 00 00 zn:5 zd:5 &lut
+LUTI2_c_1h 1100 0000 1100 11 idx:4 01 00 zn:5 zd:5 &lut
+LUTI2_c_1s 1100 0000 1100 11 idx:4 10 00 zn:5 zd:5 &lut
+
+LUTI2_c_2b 1100 0000 1000 11 idx:3 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI2_c_2h 1100 0000 1000 11 idx:3 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI2_c_2s 1100 0000 1000 11 idx:3 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2
+
+LUTI2_c_4b 1100 0000 1000 11 idx:2 10 00 00 zn:5 ... 00 &lut zd=%zd_ax4
+LUTI2_c_4h 1100 0000 1000 11 idx:2 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4
+LUTI2_c_4s 1100 0000 1000 11 idx:2 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4
+
+# LUTI2, strided (must check zd alignment)
+LUTI2_s_2b 1100 0000 1001 11 idx:3 1 00 00 zn:5 zd:5 &lut
+LUTI2_s_2h 1100 0000 1001 11 idx:3 1 01 00 zn:5 zd:5 &lut
+
+LUTI2_s_4b 1100 0000 1001 11 idx:2 10 00 00 zn:5 zd:5 &lut
+LUTI2_s_4h 1100 0000 1001 11 idx:2 10 01 00 zn:5 zd:5 &lut
+
+# LUTI4, consecutive
+LUTI4_c_1b 1100 0000 1100 101 idx:3 00 00 zn:5 zd:5 &lut
+LUTI4_c_1h 1100 0000 1100 101 idx:3 01 00 zn:5 zd:5 &lut
+LUTI4_c_1s 1100 0000 1100 101 idx:3 10 00 zn:5 zd:5 &lut
+
+LUTI4_c_2b 1100 0000 1000 101 idx:2 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI4_c_2h 1100 0000 1000 101 idx:2 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI4_c_2s 1100 0000 1000 101 idx:2 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2
+
+LUTI4_c_4h 1100 0000 1000 101 idx:1 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4
+LUTI4_c_4s 1100 0000 1000 101 idx:1 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4
+
+# LUTI4, strided (must check zd alignment)
+LUTI4_s_2b 1100 0000 1001 101 idx:2 1 00 00 zn:5 zd:5 &lut
+LUTI4_s_2h 1100 0000 1001 101 idx:2 1 01 00 zn:5 zd:5 &lut
+
+LUTI4_s_4h 1100 0000 1001 101 idx:1 10 01 00 zn:5 zd:5 &lut
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/helper-sme.h | 24 ++++++++++++++ target/arm/tcg/vec_internal.h | 15 +++++++++ target/arm/tcg/sme_helper.c | 59 ++++++++++++++++++++++++++++++++++ target/arm/tcg/sve_helper.c | 15 --------- target/arm/tcg/translate-sme.c | 56 ++++++++++++++++++++++++++++++++ target/arm/tcg/sme.decode | 42 ++++++++++++++++++++++++ 6 files changed, 196 insertions(+), 15 deletions(-)