target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-101-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 210 insertions, 0 deletions

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index 392bf7b..d9565c8 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -1188,3 +1188,27 @@ DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, 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)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index f7e4143..5a5b8ff 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -945,3 +945,45 @@ 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
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 9592f6a..d38b8a5 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1697,3 +1697,59 @@ 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, bool strided)
+{
+    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, strided | (a->idx << 1), fn);
+    }
+    return true;
+}
+
+TRANS_FEAT(LUTI2_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1b, false)
+TRANS_FEAT(LUTI2_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1h, false)
+TRANS_FEAT(LUTI2_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1s, false)
+
+TRANS_FEAT(LUTI2_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2b, false)
+TRANS_FEAT(LUTI2_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2h, false)
+TRANS_FEAT(LUTI2_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2s, false)
+
+TRANS_FEAT(LUTI2_c_4b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4b, false)
+TRANS_FEAT(LUTI2_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4h, false)
+TRANS_FEAT(LUTI2_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4s, false)
+
+TRANS_FEAT(LUTI4_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1b, false)
+TRANS_FEAT(LUTI4_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1h, false)
+TRANS_FEAT(LUTI4_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1s, false)
+
+TRANS_FEAT(LUTI4_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2b, false)
+TRANS_FEAT(LUTI4_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2h, false)
+TRANS_FEAT(LUTI4_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2s, false)
+
+TRANS_FEAT(LUTI4_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4h, false)
+TRANS_FEAT(LUTI4_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4s, false)
+
+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, true);
+}
+
+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, true);
+}
+
+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)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index d4ee6f4..0603db0 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -3443,3 +3443,91 @@ void HELPER(gvec_ursqrte_s)(void *vd, void *vn, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+static inline void do_lut_b(void *zd, uint64_t *indexes, uint64_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint8_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H1(e)] = extractn(table, index * tsize, 8);
+        }
+    }
+}
+
+static inline void do_lut_h(void *zd, uint64_t *indexes, uint64_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint16_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H2(e)] = extractn(table, index * tsize, 16);
+        }
+    }
+}
+
+static inline void do_lut_s(void *zd, uint64_t *indexes, uint32_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint32_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H4(e)] = table[H4(index)];
+        }
+    }
+}
+
+#define DO_SME2_LUT(ISIZE, NREG, SUFF, ESIZE) \
+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 elements = vl / ESIZE;                                     \
+    unsigned dstride = (!strided ? 1 : NREG == 4 ? 4 : 8);              \
+    unsigned segments = (ESIZE * 8) / (ISIZE * NREG);                   \
+    unsigned segment = idx & (segments - 1);                            \
+    ARMVectorReg indexes;                                               \
+    memcpy(&indexes, zn, vl);                                           \
+    do_lut_##SUFF(zd, indexes.d, (void *)env->za_state.zt0, elements,   \
+                  segment * NREG * elements,                            \
+                  dstride * sizeof(ARMVectorReg), ISIZE, 32, NREG);     \
+}
+
+DO_SME2_LUT(2,1,b, 1)
+DO_SME2_LUT(2,1,h, 2)
+DO_SME2_LUT(2,1,s, 4)
+DO_SME2_LUT(2,2,b, 1)
+DO_SME2_LUT(2,2,h, 2)
+DO_SME2_LUT(2,2,s, 4)
+DO_SME2_LUT(2,4,b, 1)
+DO_SME2_LUT(2,4,h, 2)
+DO_SME2_LUT(2,4,s, 4)
+
+DO_SME2_LUT(4,1,b, 1)
+DO_SME2_LUT(4,1,h, 2)
+DO_SME2_LUT(4,1,s, 4)
+DO_SME2_LUT(4,2,b, 1)
+DO_SME2_LUT(4,2,h, 2)
+DO_SME2_LUT(4,2,s, 4)
+DO_SME2_LUT(4,4,b, 1)
+DO_SME2_LUT(4,4,h, 2)
+DO_SME2_LUT(4,4,s, 4)
+
+#undef DO_SME2_LUT