haraldwolff/qemu-patch-raspberry4
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

target/arm: Implement SVE2 UQSHRN, UQRSHRN

Browse source 
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-29-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:02:54 -07:00 committed by Peter Maydell
parent 81fd3e6e4f
commit c13418da76
4 changed files with 137 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
target/arm/helper-sve.h
View file

@ -2476,6 +2476,22 @@ DEF_HELPER_FLAGS_3(sve2_sqrshrunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_sqrshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_sqrshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG,

4
target/arm/sve.decode
View file

@ -1296,6 +1296,10 @@ SHRNB 01000101 .. 1 ..... 00 0100 ..... ..... @rd_rn_tszimm_shr
SHRNT 01000101 .. 1 ..... 00 0101 ..... ..... @rd_rn_tszimm_shr
RSHRNB 01000101 .. 1 ..... 00 0110 ..... ..... @rd_rn_tszimm_shr
RSHRNT 01000101 .. 1 ..... 00 0111 ..... ..... @rd_rn_tszimm_shr
UQSHRNB 01000101 .. 1 ..... 00 1100 ..... ..... @rd_rn_tszimm_shr
UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr
UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr
UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr
## SVE2 floating-point pairwise operations

24
target/arm/sve_helper.c
View file

@ -1976,6 +1976,30 @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H)
DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S)
DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, , H1_4, DO_SQRSHRUN_D)
#define DO_UQSHRN_H(x, sh) MIN(x >> sh, UINT8_MAX)
#define DO_UQSHRN_S(x, sh) MIN(x >> sh, UINT16_MAX)
#define DO_UQSHRN_D(x, sh) MIN(x >> sh, UINT32_MAX)
DO_SHRNB(sve2_uqshrnb_h, uint16_t, uint8_t, DO_UQSHRN_H)
DO_SHRNB(sve2_uqshrnb_s, uint32_t, uint16_t, DO_UQSHRN_S)
DO_SHRNB(sve2_uqshrnb_d, uint64_t, uint32_t, DO_UQSHRN_D)
DO_SHRNT(sve2_uqshrnt_h, uint16_t, uint8_t, H1_2, H1, DO_UQSHRN_H)
DO_SHRNT(sve2_uqshrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_UQSHRN_S)
DO_SHRNT(sve2_uqshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQSHRN_D)
#define DO_UQRSHRN_H(x, sh) MIN(do_urshr(x, sh), UINT8_MAX)
#define DO_UQRSHRN_S(x, sh) MIN(do_urshr(x, sh), UINT16_MAX)
#define DO_UQRSHRN_D(x, sh) MIN(do_urshr(x, sh), UINT32_MAX)
DO_SHRNB(sve2_uqrshrnb_h, uint16_t, uint8_t, DO_UQRSHRN_H)
DO_SHRNB(sve2_uqrshrnb_s, uint32_t, uint16_t, DO_UQRSHRN_S)
DO_SHRNB(sve2_uqrshrnb_d, uint64_t, uint32_t, DO_UQRSHRN_D)
DO_SHRNT(sve2_uqrshrnt_h, uint16_t, uint8_t, H1_2, H1, DO_UQRSHRN_H)
DO_SHRNT(sve2_uqrshrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_UQRSHRN_S)
DO_SHRNT(sve2_uqrshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQRSHRN_D)
#undef DO_SHRNB
#undef DO_SHRNT

93
target/arm/translate-sve.c
View file

@ -6956,6 +6956,99 @@ static bool trans_SQRSHRUNT(DisasContext *s, arg_rri_esz *a)
return do_sve2_shr_narrow(s, a, ops);
}
static void gen_uqshrnb_vec(unsigned vece, TCGv_vec d,
TCGv_vec n, int64_t shr)
{
TCGv_vec t = tcg_temp_new_vec_matching(d);
int halfbits = 4 << vece;
tcg_gen_shri_vec(vece, n, n, shr);
tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
tcg_gen_umin_vec(vece, d, n, t);
tcg_temp_free_vec(t);
}
static bool trans_UQSHRNB(DisasContext *s, arg_rri_esz *a)
{
static const TCGOpcode vec_list[] = {
INDEX_op_shri_vec, INDEX_op_umin_vec, 0
};
static const GVecGen2i ops[3] = {
{ .fniv = gen_uqshrnb_vec,
.opt_opc = vec_list,
.fno = gen_helper_sve2_uqshrnb_h,
.vece = MO_16 },
{ .fniv = gen_uqshrnb_vec,
.opt_opc = vec_list,
.fno = gen_helper_sve2_uqshrnb_s,
.vece = MO_32 },
{ .fniv = gen_uqshrnb_vec,
.opt_opc = vec_list,
.fno = gen_helper_sve2_uqshrnb_d,
.vece = MO_64 },
};
return do_sve2_shr_narrow(s, a, ops);
}
static void gen_uqshrnt_vec(unsigned vece, TCGv_vec d,
TCGv_vec n, int64_t shr)
{
TCGv_vec t = tcg_temp_new_vec_matching(d);
int halfbits = 4 << vece;
tcg_gen_shri_vec(vece, n, n, shr);
tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
tcg_gen_umin_vec(vece, n, n, t);
tcg_gen_shli_vec(vece, n, n, halfbits);
tcg_gen_bitsel_vec(vece, d, t, d, n);
tcg_temp_free_vec(t);
}
static bool trans_UQSHRNT(DisasContext *s, arg_rri_esz *a)
{
static const TCGOpcode vec_list[] = {
INDEX_op_shli_vec, INDEX_op_shri_vec, INDEX_op_umin_vec, 0
};
static const GVecGen2i ops[3] = {
{ .fniv = gen_uqshrnt_vec,
.opt_opc = vec_list,
.load_dest = true,
.fno = gen_helper_sve2_uqshrnt_h,
.vece = MO_16 },
{ .fniv = gen_uqshrnt_vec,
.opt_opc = vec_list,
.load_dest = true,
.fno = gen_helper_sve2_uqshrnt_s,
.vece = MO_32 },
{ .fniv = gen_uqshrnt_vec,
.opt_opc = vec_list,
.load_dest = true,
.fno = gen_helper_sve2_uqshrnt_d,
.vece = MO_64 },
};
return do_sve2_shr_narrow(s, a, ops);
}
static bool trans_UQRSHRNB(DisasContext *s, arg_rri_esz *a)
{
static const GVecGen2i ops[3] = {
{ .fno = gen_helper_sve2_uqrshrnb_h },
{ .fno = gen_helper_sve2_uqrshrnb_s },
{ .fno = gen_helper_sve2_uqrshrnb_d },
};
return do_sve2_shr_narrow(s, a, ops);
}
static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a)
{
static const GVecGen2i ops[3] = {
{ .fno = gen_helper_sve2_uqrshrnt_h },
{ .fno = gen_helper_sve2_uqrshrnt_s },
{ .fno = gen_helper_sve2_uqrshrnt_d },
};
return do_sve2_shr_narrow(s, a, ops);
}
static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a,
gen_helper_gvec_4_ptr *fn)
{