[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 102/114] target/arm: Implement SVE2 bitwise shift immediate
From: |
Peter Maydell |
Subject: |
[PULL 102/114] target/arm: Implement SVE2 bitwise shift immediate |
Date: |
Tue, 25 May 2021 16:07:24 +0100 |
From: Stephen Long <steplong@quicinc.com>
Implements SQSHL/UQSHL, SRSHR/URSHR, and SQSHLU
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-81-richard.henderson@linaro.org
Message-Id: <20200430194159.24064-1-steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/helper-sve.h | 33 +++++++++++++++++++++
target/arm/sve.decode | 5 ++++
target/arm/sve_helper.c | 35 ++++++++++++++++++++++
target/arm/translate-sve.c | 60 ++++++++++++++++++++++++++++++++++++++
4 files changed, 133 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index b43ffce23ac..29a14a21f50 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2761,3 +2761,36 @@ DEF_HELPER_FLAGS_5(sve2_fcvtlt_sd, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(flogb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(flogb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(flogb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uqshl_zpzi_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_srshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_srshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_srshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_srshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_urshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_urshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_urshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_urshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqshlu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqshlu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqshlu_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqshlu_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 5469ce04143..ea98508cddc 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -340,6 +340,11 @@ ASR_zpzi 00000100 .. 000 000 100 ... .. ... .....
@rdn_pg_tszimm_shr
LSR_zpzi 00000100 .. 000 001 100 ... .. ... ..... @rdn_pg_tszimm_shr
LSL_zpzi 00000100 .. 000 011 100 ... .. ... ..... @rdn_pg_tszimm_shl
ASRD 00000100 .. 000 100 100 ... .. ... ..... @rdn_pg_tszimm_shr
+SQSHL_zpzi 00000100 .. 000 110 100 ... .. ... ..... @rdn_pg_tszimm_shl
+UQSHL_zpzi 00000100 .. 000 111 100 ... .. ... ..... @rdn_pg_tszimm_shl
+SRSHR 00000100 .. 001 100 100 ... .. ... ..... @rdn_pg_tszimm_shr
+URSHR 00000100 .. 001 101 100 ... .. ... ..... @rdn_pg_tszimm_shr
+SQSHLU 00000100 .. 001 111 100 ... .. ... ..... @rdn_pg_tszimm_shl
# SVE bitwise shift by vector (predicated)
ASR_zpzz 00000100 .. 010 000 100 ... ..... ..... @rdn_pg_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index d088b1f74ce..4afb06fb2a1 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2238,6 +2238,41 @@ DO_ZPZI(sve_asrd_h, int16_t, H1_2, DO_ASRD)
DO_ZPZI(sve_asrd_s, int32_t, H1_4, DO_ASRD)
DO_ZPZI_D(sve_asrd_d, int64_t, DO_ASRD)
+/* SVE2 bitwise shift by immediate */
+DO_ZPZI(sve2_sqshl_zpzi_b, int8_t, H1, do_sqshl_b)
+DO_ZPZI(sve2_sqshl_zpzi_h, int16_t, H1_2, do_sqshl_h)
+DO_ZPZI(sve2_sqshl_zpzi_s, int32_t, H1_4, do_sqshl_s)
+DO_ZPZI_D(sve2_sqshl_zpzi_d, int64_t, do_sqshl_d)
+
+DO_ZPZI(sve2_uqshl_zpzi_b, uint8_t, H1, do_uqshl_b)
+DO_ZPZI(sve2_uqshl_zpzi_h, uint16_t, H1_2, do_uqshl_h)
+DO_ZPZI(sve2_uqshl_zpzi_s, uint32_t, H1_4, do_uqshl_s)
+DO_ZPZI_D(sve2_uqshl_zpzi_d, uint64_t, do_uqshl_d)
+
+DO_ZPZI(sve2_srshr_b, int8_t, H1, do_srshr)
+DO_ZPZI(sve2_srshr_h, int16_t, H1_2, do_srshr)
+DO_ZPZI(sve2_srshr_s, int32_t, H1_4, do_srshr)
+DO_ZPZI_D(sve2_srshr_d, int64_t, do_srshr)
+
+DO_ZPZI(sve2_urshr_b, uint8_t, H1, do_urshr)
+DO_ZPZI(sve2_urshr_h, uint16_t, H1_2, do_urshr)
+DO_ZPZI(sve2_urshr_s, uint32_t, H1_4, do_urshr)
+DO_ZPZI_D(sve2_urshr_d, uint64_t, do_urshr)
+
+#define do_suqrshl_b(n, m) \
+ ({ uint32_t discard; do_suqrshl_bhs(n, (int8_t)m, 8, false, &discard); })
+#define do_suqrshl_h(n, m) \
+ ({ uint32_t discard; do_suqrshl_bhs(n, (int16_t)m, 16, false, &discard); })
+#define do_suqrshl_s(n, m) \
+ ({ uint32_t discard; do_suqrshl_bhs(n, m, 32, false, &discard); })
+#define do_suqrshl_d(n, m) \
+ ({ uint32_t discard; do_suqrshl_d(n, m, false, &discard); })
+
+DO_ZPZI(sve2_sqshlu_b, int8_t, H1, do_suqrshl_b)
+DO_ZPZI(sve2_sqshlu_h, int16_t, H1_2, do_suqrshl_h)
+DO_ZPZI(sve2_sqshlu_s, int32_t, H1_4, do_suqrshl_s)
+DO_ZPZI_D(sve2_sqshlu_d, int64_t, do_suqrshl_d)
+
#undef DO_ASRD
#undef DO_ZPZI
#undef DO_ZPZI_D
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index b2aa9130b64..92c0620bc8e 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -1044,6 +1044,66 @@ static bool trans_ASRD(DisasContext *s, arg_rpri_esz *a)
}
}
+static bool trans_SQSHL_zpzi(DisasContext *s, arg_rpri_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_sqshl_zpzi_b, gen_helper_sve2_sqshl_zpzi_h,
+ gen_helper_sve2_sqshl_zpzi_s, gen_helper_sve2_sqshl_zpzi_d,
+ };
+ if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ return do_zpzi_ool(s, a, fns[a->esz]);
+}
+
+static bool trans_UQSHL_zpzi(DisasContext *s, arg_rpri_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_uqshl_zpzi_b, gen_helper_sve2_uqshl_zpzi_h,
+ gen_helper_sve2_uqshl_zpzi_s, gen_helper_sve2_uqshl_zpzi_d,
+ };
+ if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ return do_zpzi_ool(s, a, fns[a->esz]);
+}
+
+static bool trans_SRSHR(DisasContext *s, arg_rpri_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_srshr_b, gen_helper_sve2_srshr_h,
+ gen_helper_sve2_srshr_s, gen_helper_sve2_srshr_d,
+ };
+ if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ return do_zpzi_ool(s, a, fns[a->esz]);
+}
+
+static bool trans_URSHR(DisasContext *s, arg_rpri_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_urshr_b, gen_helper_sve2_urshr_h,
+ gen_helper_sve2_urshr_s, gen_helper_sve2_urshr_d,
+ };
+ if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ return do_zpzi_ool(s, a, fns[a->esz]);
+}
+
+static bool trans_SQSHLU(DisasContext *s, arg_rpri_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_sqshlu_b, gen_helper_sve2_sqshlu_h,
+ gen_helper_sve2_sqshlu_s, gen_helper_sve2_sqshlu_d,
+ };
+ if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ return do_zpzi_ool(s, a, fns[a->esz]);
+}
+
/*
*** SVE Bitwise Shift - Predicated Group
*/
--
2.20.1
- [PULL 095/114] target/arm: Implement SVE2 FCVTLT, Peter Maydell, 2021/05/25
- [PULL 096/114] target/arm: Implement SVE2 FCVTXNT, FCVTX, Peter Maydell, 2021/05/25
- [PULL 099/114] target/arm: Tidy do_ldrq, Peter Maydell, 2021/05/25
- [PULL 100/114] target/arm: Implement SVE2 LD1RO, Peter Maydell, 2021/05/25
- [PULL 103/114] target/arm: Move endian adjustment macros to vec_internal.h, Peter Maydell, 2021/05/25
- [PULL 102/114] target/arm: Implement SVE2 bitwise shift immediate,
Peter Maydell <=
- [PULL 106/114] target/arm: Split out do_neon_ddda_fpst, Peter Maydell, 2021/05/25
- [PULL 108/114] target/arm: Fix decode for VDOT (indexed), Peter Maydell, 2021/05/25
- [PULL 109/114] target/arm: Split out do_neon_ddda, Peter Maydell, 2021/05/25
- [PULL 101/114] target/arm: Implement 128-bit ZIP, UZP, TRN, Peter Maydell, 2021/05/25
- [PULL 104/114] target/arm: Implement SVE2 fp multiply-add long, Peter Maydell, 2021/05/25
- [PULL 105/114] target/arm: Implement aarch64 SUDOT, USDOT, Peter Maydell, 2021/05/25
- [PULL 110/114] target/arm: Split decode of VSDOT and VUDOT, Peter Maydell, 2021/05/25
- [PULL 114/114] target/arm: Enable SVE2 and related extensions, Peter Maydell, 2021/05/25
- [PULL 107/114] target/arm: Remove unused fpst from VDOT_scalar, Peter Maydell, 2021/05/25
- [PULL 112/114] target/arm: Implement integer matrix multiply accumulate, Peter Maydell, 2021/05/25