OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) 

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-7-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-24 18:02:32 -07:00 committed by Peter Maydell
parent 8b3f15b0a3
commit 45d9503d0a
4 changed files with 176 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
target/arm/helper-sve.h
View File

@ -172,6 +172,60 @@ DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG,

17
target/arm/sve.decode
View File

@ -1112,3 +1112,20 @@ URECPE 01000100 .. 000 000 101 ... ..... ..... @rd_pg_rn
URSQRTE 01000100 .. 000 001 101 ... ..... ..... @rd_pg_rn
SQABS 01000100 .. 001 000 101 ... ..... ..... @rd_pg_rn
SQNEG 01000100 .. 001 001 101 ... ..... ..... @rd_pg_rn
### SVE2 saturating/rounding bitwise shift left (predicated)
SRSHL 01000100 .. 000 010 100 ... ..... ..... @rdn_pg_rm
URSHL 01000100 .. 000 011 100 ... ..... ..... @rdn_pg_rm
SRSHL 01000100 .. 000 110 100 ... ..... ..... @rdm_pg_rn # SRSHLR
URSHL 01000100 .. 000 111 100 ... ..... ..... @rdm_pg_rn # URSHLR
SQSHL 01000100 .. 001 000 100 ... ..... ..... @rdn_pg_rm
UQSHL 01000100 .. 001 001 100 ... ..... ..... @rdn_pg_rm
SQSHL 01000100 .. 001 100 100 ... ..... ..... @rdm_pg_rn # SQSHLR
UQSHL 01000100 .. 001 101 100 ... ..... ..... @rdm_pg_rn # UQSHLR
SQRSHL 01000100 .. 001 010 100 ... ..... ..... @rdn_pg_rm
UQRSHL 01000100 .. 001 011 100 ... ..... ..... @rdn_pg_rm
SQRSHL 01000100 .. 001 110 100 ... ..... ..... @rdm_pg_rn # SQRSHLR
UQRSHL 01000100 .. 001 111 100 ... ..... ..... @rdm_pg_rn # UQRSHLR

87
target/arm/sve_helper.c
View File

@ -26,6 +26,7 @@
#include "tcg/tcg-gvec-desc.h"
#include "fpu/softfloat.h"
#include "tcg/tcg.h"
#include "vec_internal.h"
/* Note that vector data is stored in host-endian 64-bit chunks,
@ -561,6 +562,92 @@ DO_ZPZZ(sve2_uadalp_zpzz_h, uint16_t, H1_2, do_uadalp_h)
DO_ZPZZ(sve2_uadalp_zpzz_s, uint32_t, H1_4, do_uadalp_s)
DO_ZPZZ_D(sve2_uadalp_zpzz_d, uint64_t, do_uadalp_d)
#define do_srshl_b(n, m) do_sqrshl_bhs(n, m, 8, true, NULL)
#define do_srshl_h(n, m) do_sqrshl_bhs(n, m, 16, true, NULL)
#define do_srshl_s(n, m) do_sqrshl_bhs(n, m, 32, true, NULL)
#define do_srshl_d(n, m) do_sqrshl_d(n, m, true, NULL)
DO_ZPZZ(sve2_srshl_zpzz_b, int8_t, H1, do_srshl_b)
DO_ZPZZ(sve2_srshl_zpzz_h, int16_t, H1_2, do_srshl_h)
DO_ZPZZ(sve2_srshl_zpzz_s, int32_t, H1_4, do_srshl_s)
DO_ZPZZ_D(sve2_srshl_zpzz_d, int64_t, do_srshl_d)
#define do_urshl_b(n, m) do_uqrshl_bhs(n, (int8_t)m, 8, true, NULL)
#define do_urshl_h(n, m) do_uqrshl_bhs(n, (int16_t)m, 16, true, NULL)
#define do_urshl_s(n, m) do_uqrshl_bhs(n, m, 32, true, NULL)
#define do_urshl_d(n, m) do_uqrshl_d(n, m, true, NULL)
DO_ZPZZ(sve2_urshl_zpzz_b, uint8_t, H1, do_urshl_b)
DO_ZPZZ(sve2_urshl_zpzz_h, uint16_t, H1_2, do_urshl_h)
DO_ZPZZ(sve2_urshl_zpzz_s, uint32_t, H1_4, do_urshl_s)
DO_ZPZZ_D(sve2_urshl_zpzz_d, uint64_t, do_urshl_d)
/*
* Unlike the NEON and AdvSIMD versions, there is no QC bit to set.
* We pass in a pointer to a dummy saturation field to trigger
* the saturating arithmetic but discard the information about
* whether it has occurred.
*/
#define do_sqshl_b(n, m) \
({ uint32_t discard; do_sqrshl_bhs(n, m, 8, false, &discard); })
#define do_sqshl_h(n, m) \
({ uint32_t discard; do_sqrshl_bhs(n, m, 16, false, &discard); })
#define do_sqshl_s(n, m) \
({ uint32_t discard; do_sqrshl_bhs(n, m, 32, false, &discard); })
#define do_sqshl_d(n, m) \
({ uint32_t discard; do_sqrshl_d(n, m, false, &discard); })
DO_ZPZZ(sve2_sqshl_zpzz_b, int8_t, H1_2, do_sqshl_b)
DO_ZPZZ(sve2_sqshl_zpzz_h, int16_t, H1_2, do_sqshl_h)
DO_ZPZZ(sve2_sqshl_zpzz_s, int32_t, H1_4, do_sqshl_s)
DO_ZPZZ_D(sve2_sqshl_zpzz_d, int64_t, do_sqshl_d)
#define do_uqshl_b(n, m) \
({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, false, &discard); })
#define do_uqshl_h(n, m) \
({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, false, &discard); })
#define do_uqshl_s(n, m) \
({ uint32_t discard; do_uqrshl_bhs(n, m, 32, false, &discard); })
#define do_uqshl_d(n, m) \
({ uint32_t discard; do_uqrshl_d(n, m, false, &discard); })
DO_ZPZZ(sve2_uqshl_zpzz_b, uint8_t, H1_2, do_uqshl_b)
DO_ZPZZ(sve2_uqshl_zpzz_h, uint16_t, H1_2, do_uqshl_h)
DO_ZPZZ(sve2_uqshl_zpzz_s, uint32_t, H1_4, do_uqshl_s)
DO_ZPZZ_D(sve2_uqshl_zpzz_d, uint64_t, do_uqshl_d)
#define do_sqrshl_b(n, m) \
({ uint32_t discard; do_sqrshl_bhs(n, m, 8, true, &discard); })
#define do_sqrshl_h(n, m) \
({ uint32_t discard; do_sqrshl_bhs(n, m, 16, true, &discard); })
#define do_sqrshl_s(n, m) \
({ uint32_t discard; do_sqrshl_bhs(n, m, 32, true, &discard); })
#define do_sqrshl_d(n, m) \
({ uint32_t discard; do_sqrshl_d(n, m, true, &discard); })
DO_ZPZZ(sve2_sqrshl_zpzz_b, int8_t, H1_2, do_sqrshl_b)
DO_ZPZZ(sve2_sqrshl_zpzz_h, int16_t, H1_2, do_sqrshl_h)
DO_ZPZZ(sve2_sqrshl_zpzz_s, int32_t, H1_4, do_sqrshl_s)
DO_ZPZZ_D(sve2_sqrshl_zpzz_d, int64_t, do_sqrshl_d)
#undef do_sqrshl_d
#define do_uqrshl_b(n, m) \
({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, true, &discard); })
#define do_uqrshl_h(n, m) \
({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, true, &discard); })
#define do_uqrshl_s(n, m) \
({ uint32_t discard; do_uqrshl_bhs(n, m, 32, true, &discard); })
#define do_uqrshl_d(n, m) \
({ uint32_t discard; do_uqrshl_d(n, m, true, &discard); })
DO_ZPZZ(sve2_uqrshl_zpzz_b, uint8_t, H1_2, do_uqrshl_b)
DO_ZPZZ(sve2_uqrshl_zpzz_h, uint16_t, H1_2, do_uqrshl_h)
DO_ZPZZ(sve2_uqrshl_zpzz_s, uint32_t, H1_4, do_uqrshl_s)
DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d)
#undef do_uqrshl_d
#undef DO_ZPZZ
#undef DO_ZPZZ_D

18
target/arm/translate-sve.c
View File

@ -5931,3 +5931,21 @@ static bool trans_SQNEG(DisasContext *s, arg_rpr_esz *a)
};
return do_sve2_zpz_ool(s, a, fns[a->esz]);
}
#define DO_SVE2_ZPZZ(NAME, name) \
static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \
{ \
static gen_helper_gvec_4 * const fns[4] = { \
gen_helper_sve2_##name##_zpzz_b, gen_helper_sve2_##name##_zpzz_h, \
gen_helper_sve2_##name##_zpzz_s, gen_helper_sve2_##name##_zpzz_d, \
}; \
return do_sve2_zpzz_ool(s, a, fns[a->esz]); \
}
DO_SVE2_ZPZZ(SQSHL, sqshl)
DO_SVE2_ZPZZ(SQRSHL, sqrshl)
DO_SVE2_ZPZZ(SRSHL, srshl)
DO_SVE2_ZPZZ(UQSHL, uqshl)
DO_SVE2_ZPZZ(UQRSHL, uqrshl)
DO_SVE2_ZPZZ(URSHL, urshl)