[PATCH v5 17/81] target/arm: Implement SVE2 bitwise permute

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/cpu.h           |  5 +++
 target/arm/helper-sve.h    | 15 ++++++++
 target/arm/sve.decode      |  6 ++++
 target/arm/sve_helper.c    | 73 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 36 +++++++++++++++++++
 5 files changed, 135 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 902579d24b..ae787fac8a 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -4241,6 +4241,11 @@ static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2;
 }
 
+static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0;
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index f65818da05..4861481fe0 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2377,3 +2377,18 @@ DEF_HELPER_FLAGS_4(sve2_eoril_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_eoril_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_eoril_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_eoril_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_bext_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bext_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bext_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bext_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_bdep_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bdep_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bdep_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bdep_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_bgrp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bgrp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bgrp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bgrp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 0922a44829..7cb89a0d47 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1220,3 +1220,9 @@ USHLLT          01000101 .. 0 ..... 1010 11 ..... .....  @rd_rn_tszimm_shl
 
 EORBT           01000101 .. 0 ..... 10010 0 ..... .....  @rd_rn_rm
 EORTB           01000101 .. 0 ..... 10010 1 ..... .....  @rd_rn_rm
+
+## SVE2 bitwise permute
+
+BEXT            01000101 .. 0 ..... 1011 00 ..... .....  @rd_rn_rm
+BDEP            01000101 .. 0 ..... 1011 01 ..... .....  @rd_rn_rm
+BGRP            01000101 .. 0 ..... 1011 10 ..... .....  @rd_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 1de0a9bdc3..d692d2fe3d 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1241,6 +1241,79 @@ DO_ZZZ_NTB(sve2_eoril_d, uint64_t,     , DO_EOR)
 
 #undef DO_ZZZ_NTB
 
+#define DO_BITPERM(NAME, TYPE, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{                                                              \
+    intptr_t i, opr_sz = simd_oprsz(desc);                     \
+    for (i = 0; i < opr_sz; i += sizeof(TYPE)) {               \
+        TYPE nn = *(TYPE *)(vn + i);                           \
+        TYPE mm = *(TYPE *)(vm + i);                           \
+        *(TYPE *)(vd + i) = OP(nn, mm, sizeof(TYPE) * 8);      \
+    }                                                          \
+}
+
+static uint64_t bitextract(uint64_t data, uint64_t mask, int n)
+{
+    uint64_t res = 0;
+    int db, rb = 0;
+
+    for (db = 0; db < n; ++db) {
+        if ((mask >> db) & 1) {
+            res |= ((data >> db) & 1) << rb;
+            ++rb;
+        }
+    }
+    return res;
+}
+
+DO_BITPERM(sve2_bext_b, uint8_t, bitextract)
+DO_BITPERM(sve2_bext_h, uint16_t, bitextract)
+DO_BITPERM(sve2_bext_s, uint32_t, bitextract)
+DO_BITPERM(sve2_bext_d, uint64_t, bitextract)
+
+static uint64_t bitdeposit(uint64_t data, uint64_t mask, int n)
+{
+    uint64_t res = 0;
+    int rb, db = 0;
+
+    for (rb = 0; rb < n; ++rb) {
+        if ((mask >> rb) & 1) {
+            res |= ((data >> db) & 1) << rb;
+            ++db;
+        }
+    }
+    return res;
+}
+
+DO_BITPERM(sve2_bdep_b, uint8_t, bitdeposit)
+DO_BITPERM(sve2_bdep_h, uint16_t, bitdeposit)
+DO_BITPERM(sve2_bdep_s, uint32_t, bitdeposit)
+DO_BITPERM(sve2_bdep_d, uint64_t, bitdeposit)
+
+static uint64_t bitgroup(uint64_t data, uint64_t mask, int n)
+{
+    uint64_t resm = 0, resu = 0;
+    int db, rbm = 0, rbu = 0;
+
+    for (db = 0; db < n; ++db) {
+        uint64_t val = (data >> db) & 1;
+        if ((mask >> db) & 1) {
+            resm |= val << rbm++;
+        } else {
+            resu |= val << rbu++;
+        }
+    }
+
+    return resm | (resu << rbm);
+}
+
+DO_BITPERM(sve2_bgrp_b, uint8_t, bitgroup)
+DO_BITPERM(sve2_bgrp_h, uint16_t, bitgroup)
+DO_BITPERM(sve2_bgrp_s, uint32_t, bitgroup)
+DO_BITPERM(sve2_bgrp_d, uint64_t, bitgroup)
+
+#undef DO_BITPERM
+
 #define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \
 void HELPER(NAME)(void *vd, void *vn, uint32_t desc)           \
 {                                                              \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 509b3bc68c..da2f67fb67 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6249,3 +6249,39 @@ static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a)
 {
     return do_sve2_shll_tb(s, a, true, true);
 }
+
+static bool trans_BEXT(DisasContext *s, arg_rrr_esz *a)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_sve2_bext_b, gen_helper_sve2_bext_h,
+        gen_helper_sve2_bext_s, gen_helper_sve2_bext_d,
+    };
+    if (!dc_isar_feature(aa64_sve2_bitperm, s)) {
+        return false;
+    }
+    return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
+}
+
+static bool trans_BDEP(DisasContext *s, arg_rrr_esz *a)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h,
+        gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d,
+    };
+    if (!dc_isar_feature(aa64_sve2_bitperm, s)) {
+        return false;
+    }
+    return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
+}
+
+static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h,
+        gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d,
+    };
+    if (!dc_isar_feature(aa64_sve2_bitperm, s)) {
+        return false;
+    }
+    return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
+}
-- 
2.25.1