ShuriZma
/
xemu
mirror of https://github.com/xemu-project/xemu.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

target/arm: Implement SVE2 bitwise permute 

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-18-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:02:43 -07:00 committed by Peter Maydell
parent 2df3ca5599
commit cb9c33b817
5 changed files with 135 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
target/arm/cpu.h
View File

@ -4251,6 +4251,11 @@ 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?"
*/

15
target/arm/helper-sve.h
View File

@ -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)

6
target/arm/sve.decode
View File

@ -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

73
target/arm/sve_helper.c
View File

@ -1246,6 +1246,79 @@ 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) \
{ \

36
target/arm/translate-sve.c
View File

@ -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);
}