[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 028/114] target/arm: Implement SVE2 saturating/rounding bitwise sh
From: |
Peter Maydell |
Subject: |
[PULL 028/114] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) |
Date: |
Tue, 25 May 2021 16:01:58 +0100 |
From: Richard Henderson <richard.henderson@linaro.org>
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>
---
target/arm/helper-sve.h | 54 +++++++++++++++++++++++
target/arm/sve.decode | 17 ++++++++
target/arm/sve_helper.c | 87 ++++++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 18 ++++++++
4 files changed, 176 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 9992e93e2b8..62106c74be2 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -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,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 5ba542969b4..93f2479693f 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -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
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 7a08c24f2dd..17c6440b06e 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -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
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index c30b3c476e0..6c1561d897c 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -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)
--
2.20.1
- [PULL 014/114] accel/tcg: Add tlb_flush_range_by_mmuidx(), (continued)
- [PULL 014/114] accel/tcg: Add tlb_flush_range_by_mmuidx(), Peter Maydell, 2021/05/25
- [PULL 015/114] accel/tcg: Add tlb_flush_range_by_mmuidx_all_cpus(), Peter Maydell, 2021/05/25
- [PULL 020/114] target/arm: Add support for FEAT_TLBIOS, Peter Maydell, 2021/05/25
- [PULL 021/114] target/arm: set ID_AA64ISAR0.TLB to 2 for max AARCH64 CPU type, Peter Maydell, 2021/05/25
- [PULL 019/114] target/arm: Add support for FEAT_TLBIRANGE, Peter Maydell, 2021/05/25
- [PULL 023/114] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2, Peter Maydell, 2021/05/25
- [PULL 024/114] target/arm: Implement SVE2 Integer Multiply - Unpredicated, Peter Maydell, 2021/05/25
- [PULL 022/114] disas/libvixl: Protect C system header for C++ compiler, Peter Maydell, 2021/05/25
- [PULL 025/114] target/arm: Implement SVE2 integer pairwise add and accumulate long, Peter Maydell, 2021/05/25
- [PULL 026/114] target/arm: Implement SVE2 integer unary operations (predicated), Peter Maydell, 2021/05/25
- [PULL 028/114] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated),
Peter Maydell <=
- [PULL 030/114] target/arm: Implement SVE2 integer pairwise arithmetic, Peter Maydell, 2021/05/25
- [PULL 031/114] target/arm: Implement SVE2 saturating add/subtract (predicated), Peter Maydell, 2021/05/25
- [PULL 029/114] target/arm: Implement SVE2 integer halving add/subtract (predicated), Peter Maydell, 2021/05/25
- [PULL 027/114] target/arm: Split out saturating/rounding shifts from neon, Peter Maydell, 2021/05/25
- [PULL 034/114] target/arm: Implement SVE2 integer add/subtract wide, Peter Maydell, 2021/05/25
- [PULL 040/114] target/arm: Implement SVE2 complex integer add, Peter Maydell, 2021/05/25
- [PULL 039/114] target/arm: Implement SVE2 bitwise permute, Peter Maydell, 2021/05/25
- [PULL 036/114] target/arm: Implement SVE2 PMULLB, PMULLT, Peter Maydell, 2021/05/25
- [PULL 047/114] target/arm: Implement SVE2 floating-point pairwise, Peter Maydell, 2021/05/25
- [PULL 032/114] target/arm: Implement SVE2 integer add/subtract long, Peter Maydell, 2021/05/25