From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: peter.maydell@linaro.org, qemu-arm@nongnu.org, alex.bennee@linaro.org
Subject: [PATCH v4 74/78] target/arm: Implement 128-bit ZIP, UZP, TRN
Date: Tue, 9 Mar 2021 08:20:37 -0800 [thread overview]
Message-ID: <20210309162041.23124-75-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210309162041.23124-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper-sve.h | 3 ++
target/arm/sve.decode | 8 ++++++
target/arm/sve_helper.c | 29 +++++++++++++------
target/arm/translate-sve.c | 58 ++++++++++++++++++++++++++++++++++++++
4 files changed, 90 insertions(+), 8 deletions(-)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 0a0ee8587b..ddda7f35ed 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -689,16 +689,19 @@ DEF_HELPER_FLAGS_4(sve_zip_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_zip_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_zip_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_zip_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_zip_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_uzp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_uzp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_uzp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_uzp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uzp_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_trn_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_trn_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_trn_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_trn_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_trn_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_compact_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_compact_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index f3b405b741..78452d416d 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -592,6 +592,14 @@ UZP2_z 00000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm
TRN1_z 00000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm
TRN2_z 00000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm
+# SVE2 permute vector segments
+ZIP1_q 00000101 10 1 ..... 000 000 ..... ..... @rd_rn_rm_e0
+ZIP2_q 00000101 10 1 ..... 000 001 ..... ..... @rd_rn_rm_e0
+UZP1_q 00000101 10 1 ..... 000 010 ..... ..... @rd_rn_rm_e0
+UZP2_q 00000101 10 1 ..... 000 011 ..... ..... @rd_rn_rm_e0
+TRN1_q 00000101 10 1 ..... 000 110 ..... ..... @rd_rn_rm_e0
+TRN2_q 00000101 10 1 ..... 000 111 ..... ..... @rd_rn_rm_e0
+
### SVE Permute - Predicated Group
# SVE compress active elements
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 1e7c9c4f66..d879ffce9e 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -3458,36 +3458,45 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
*(TYPE *)(vd + H(2 * i + 0)) = *(TYPE *)(vn + H(i)); \
*(TYPE *)(vd + H(2 * i + sizeof(TYPE))) = *(TYPE *)(vm + H(i)); \
} \
+ if (sizeof(TYPE) == 16 && unlikely(oprsz & 16)) { \
+ memset(vd + oprsz - 16, 0, 16); \
+ } \
}
DO_ZIP(sve_zip_b, uint8_t, H1)
DO_ZIP(sve_zip_h, uint16_t, H1_2)
DO_ZIP(sve_zip_s, uint32_t, H1_4)
DO_ZIP(sve_zip_d, uint64_t, )
+DO_ZIP(sve2_zip_q, Int128, )
#define DO_UZP(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
{ \
intptr_t oprsz = simd_oprsz(desc); \
- intptr_t oprsz_2 = oprsz / 2; \
intptr_t odd_ofs = simd_data(desc); \
- intptr_t i; \
+ intptr_t i, p; \
ARMVectorReg tmp_m; \
if (unlikely((vm - vd) < (uintptr_t)oprsz)) { \
vm = memcpy(&tmp_m, vm, oprsz); \
} \
- for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \
- *(TYPE *)(vd + H(i)) = *(TYPE *)(vn + H(2 * i + odd_ofs)); \
- } \
- for (i = 0; i < oprsz_2; i += sizeof(TYPE)) { \
- *(TYPE *)(vd + H(oprsz_2 + i)) = *(TYPE *)(vm + H(2 * i + odd_ofs)); \
- } \
+ i = 0, p = odd_ofs; \
+ do { \
+ *(TYPE *)(vd + H(i)) = *(TYPE *)(vn + H(p)); \
+ i += sizeof(TYPE), p += 2 * sizeof(TYPE); \
+ } while (p < oprsz); \
+ p -= oprsz; \
+ do { \
+ *(TYPE *)(vd + H(i)) = *(TYPE *)(vm + H(p)); \
+ i += sizeof(TYPE), p += 2 * sizeof(TYPE); \
+ } while (p < oprsz); \
+ tcg_debug_assert(i == oprsz); \
}
DO_UZP(sve_uzp_b, uint8_t, H1)
DO_UZP(sve_uzp_h, uint16_t, H1_2)
DO_UZP(sve_uzp_s, uint32_t, H1_4)
DO_UZP(sve_uzp_d, uint64_t, )
+DO_UZP(sve2_uzp_q, Int128, )
#define DO_TRN(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
@@ -3501,12 +3510,16 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
*(TYPE *)(vd + H(i + 0)) = ae; \
*(TYPE *)(vd + H(i + sizeof(TYPE))) = be; \
} \
+ if (sizeof(TYPE) == 16 && unlikely(oprsz & 16)) { \
+ memset(vd + oprsz - 16, 0, 16); \
+ } \
}
DO_TRN(sve_trn_b, uint8_t, H1)
DO_TRN(sve_trn_h, uint16_t, H1_2)
DO_TRN(sve_trn_s, uint32_t, H1_4)
DO_TRN(sve_trn_d, uint64_t, )
+DO_TRN(sve2_trn_q, Int128, )
#undef DO_ZIP
#undef DO_UZP
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 58bebbfedd..ef2ca6a0b6 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -2624,6 +2624,32 @@ static bool trans_ZIP2_z(DisasContext *s, arg_rrr_esz *a)
return do_zip(s, a, true);
}
+static bool do_zip_q(DisasContext *s, arg_rrr_esz *a, bool high)
+{
+ if (!dc_isar_feature(aa64_sve2_f64mm, s)) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ unsigned high_ofs = high ? QEMU_ALIGN_DOWN(vsz, 32) / 2 : 0;
+ tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn) + high_ofs,
+ vec_full_reg_offset(s, a->rm) + high_ofs,
+ vsz, vsz, 0, gen_helper_sve2_zip_q);
+ }
+ return true;
+}
+
+static bool trans_ZIP1_q(DisasContext *s, arg_rrr_esz *a)
+{
+ return do_zip_q(s, a, false);
+}
+
+static bool trans_ZIP2_q(DisasContext *s, arg_rrr_esz *a)
+{
+ return do_zip_q(s, a, true);
+}
+
static gen_helper_gvec_3 * const uzp_fns[4] = {
gen_helper_sve_uzp_b, gen_helper_sve_uzp_h,
gen_helper_sve_uzp_s, gen_helper_sve_uzp_d,
@@ -2639,6 +2665,22 @@ static bool trans_UZP2_z(DisasContext *s, arg_rrr_esz *a)
return do_zzz_data_ool(s, a, 1 << a->esz, uzp_fns[a->esz]);
}
+static bool trans_UZP1_q(DisasContext *s, arg_rrr_esz *a)
+{
+ if (!dc_isar_feature(aa64_sve2_f64mm, s)) {
+ return false;
+ }
+ return do_zzz_data_ool(s, a, 0, gen_helper_sve2_uzp_q);
+}
+
+static bool trans_UZP2_q(DisasContext *s, arg_rrr_esz *a)
+{
+ if (!dc_isar_feature(aa64_sve2_f64mm, s)) {
+ return false;
+ }
+ return do_zzz_data_ool(s, a, 16, gen_helper_sve2_uzp_q);
+}
+
static gen_helper_gvec_3 * const trn_fns[4] = {
gen_helper_sve_trn_b, gen_helper_sve_trn_h,
gen_helper_sve_trn_s, gen_helper_sve_trn_d,
@@ -2654,6 +2696,22 @@ static bool trans_TRN2_z(DisasContext *s, arg_rrr_esz *a)
return do_zzz_data_ool(s, a, 1 << a->esz, trn_fns[a->esz]);
}
+static bool trans_TRN1_q(DisasContext *s, arg_rrr_esz *a)
+{
+ if (!dc_isar_feature(aa64_sve2_f64mm, s)) {
+ return false;
+ }
+ return do_zzz_data_ool(s, a, 0, gen_helper_sve2_trn_q);
+}
+
+static bool trans_TRN2_q(DisasContext *s, arg_rrr_esz *a)
+{
+ if (!dc_isar_feature(aa64_sve2_f64mm, s)) {
+ return false;
+ }
+ return do_zzz_data_ool(s, a, 16, gen_helper_sve2_trn_q);
+}
+
/*
*** SVE Permute Vector - Predicated Group
*/
--
2.25.1
next prev parent reply other threads:[~2021-03-09 18:29 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-09 16:19 [PATCH v4 00/78] target/arm: Implement SVE2 Richard Henderson
2021-03-09 16:19 ` [PATCH v4 01/78] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2 Richard Henderson
2021-03-09 16:19 ` [PATCH v4 02/78] target/arm: Implement SVE2 Integer Multiply - Unpredicated Richard Henderson
2021-03-09 16:19 ` [PATCH v4 03/78] target/arm: Implement SVE2 integer pairwise add and accumulate long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 04/78] target/arm: Implement SVE2 integer unary operations (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 05/78] target/arm: Split out saturating/rounding shifts from neon Richard Henderson
2021-03-09 16:19 ` [PATCH v4 06/78] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 07/78] target/arm: Implement SVE2 integer halving add/subtract (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 08/78] target/arm: Implement SVE2 integer pairwise arithmetic Richard Henderson
2021-03-09 16:19 ` [PATCH v4 09/78] target/arm: Implement SVE2 saturating add/subtract (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 10/78] target/arm: Implement SVE2 integer add/subtract long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 11/78] target/arm: Implement SVE2 integer add/subtract interleaved long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 12/78] target/arm: Implement SVE2 integer add/subtract wide Richard Henderson
2021-03-09 16:19 ` [PATCH v4 13/78] target/arm: Implement SVE2 integer multiply long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 14/78] target/arm: Implement PMULLB and PMULLT Richard Henderson
2021-03-09 16:19 ` [PATCH v4 15/78] target/arm: Implement SVE2 bitwise shift left long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 16/78] target/arm: Implement SVE2 bitwise exclusive-or interleaved Richard Henderson
2021-03-09 16:19 ` [PATCH v4 17/78] target/arm: Implement SVE2 bitwise permute Richard Henderson
2021-03-09 16:19 ` [PATCH v4 18/78] target/arm: Implement SVE2 complex integer add Richard Henderson
2021-03-09 16:19 ` [PATCH v4 19/78] target/arm: Implement SVE2 integer absolute difference and accumulate long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 20/78] target/arm: Implement SVE2 integer add/subtract long with carry Richard Henderson
2021-03-09 16:19 ` [PATCH v4 21/78] target/arm: Implement SVE2 bitwise shift right and accumulate Richard Henderson
2021-03-09 16:19 ` [PATCH v4 22/78] target/arm: Implement SVE2 bitwise shift and insert Richard Henderson
2021-03-09 16:19 ` [PATCH v4 23/78] target/arm: Implement SVE2 integer absolute difference and accumulate Richard Henderson
2021-03-09 16:19 ` [PATCH v4 24/78] target/arm: Implement SVE2 saturating extract narrow Richard Henderson
2021-03-09 16:19 ` [PATCH v4 25/78] target/arm: Implement SVE2 floating-point pairwise Richard Henderson
2021-03-09 16:19 ` [PATCH v4 26/78] target/arm: Implement SVE2 SHRN, RSHRN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 27/78] target/arm: Implement SVE2 SQSHRUN, SQRSHRUN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 28/78] target/arm: Implement SVE2 UQSHRN, UQRSHRN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 29/78] target/arm: Implement SVE2 SQSHRN, SQRSHRN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 30/78] target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS Richard Henderson
2021-03-09 16:19 ` [PATCH v4 31/78] target/arm: Implement SVE2 WHILERW, WHILEWR Richard Henderson
2021-03-09 16:19 ` [PATCH v4 32/78] target/arm: Implement SVE2 bitwise ternary operations Richard Henderson
2021-03-09 16:19 ` [PATCH v4 33/78] target/arm: Implement SVE2 MATCH, NMATCH Richard Henderson
2021-03-09 16:19 ` [PATCH v4 34/78] target/arm: Implement SVE2 saturating multiply-add long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 35/78] target/arm: Implement SVE2 saturating multiply-add high Richard Henderson
2021-03-09 16:19 ` [PATCH v4 36/78] target/arm: Implement SVE2 integer multiply-add long Richard Henderson
2021-03-09 16:20 ` [PATCH v4 37/78] target/arm: Implement SVE2 complex integer multiply-add Richard Henderson
2021-03-09 16:20 ` [PATCH v4 38/78] target/arm: Implement SVE2 ADDHNB, ADDHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 39/78] target/arm: Implement SVE2 RADDHNB, RADDHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 40/78] target/arm: Implement SVE2 SUBHNB, SUBHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 41/78] target/arm: Implement SVE2 RSUBHNB, RSUBHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 42/78] target/arm: Implement SVE2 HISTCNT, HISTSEG Richard Henderson
2021-03-09 16:20 ` [PATCH v4 43/78] target/arm: Implement SVE2 XAR Richard Henderson
2021-03-09 16:20 ` [PATCH v4 44/78] target/arm: Implement SVE2 scatter store insns Richard Henderson
2021-03-09 16:20 ` [PATCH v4 45/78] target/arm: Implement SVE2 gather load insns Richard Henderson
2021-03-09 16:20 ` [PATCH v4 46/78] target/arm: Implement SVE2 FMMLA Richard Henderson
2021-03-09 16:20 ` [PATCH v4 47/78] target/arm: Implement SVE2 SPLICE, EXT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 48/78] target/arm: Pass separate addend to {U, S}DOT helpers Richard Henderson
2021-03-09 16:20 ` [PATCH v4 49/78] target/arm: Pass separate addend to FCMLA helpers Richard Henderson
2021-03-09 16:20 ` [PATCH v4 50/78] target/arm: Split out formats for 2 vectors + 1 index Richard Henderson
2021-03-09 16:20 ` [PATCH v4 51/78] target/arm: Split out formats for 3 " Richard Henderson
2021-03-09 16:20 ` [PATCH v4 52/78] target/arm: Implement SVE2 integer multiply (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 53/78] target/arm: Implement SVE2 integer multiply-add (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 54/78] target/arm: Implement SVE2 saturating multiply-add high (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 55/78] target/arm: Implement SVE2 saturating multiply-add (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 56/78] target/arm: Implement SVE2 integer multiply long (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 57/78] target/arm: Implement SVE2 saturating multiply (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 58/78] target/arm: Implement SVE2 signed saturating doubling multiply high Richard Henderson
2021-03-09 16:20 ` [PATCH v4 59/78] target/arm: Implement SVE2 saturating multiply high (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 60/78] target/arm: Implement SVE2 multiply-add long (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 61/78] target/arm: Implement SVE2 complex integer multiply-add (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 62/78] target/arm: Implement SVE mixed sign dot product (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 63/78] target/arm: Implement SVE mixed sign dot product Richard Henderson
2021-03-09 16:20 ` [PATCH v4 64/78] target/arm: Implement SVE2 crypto unary operations Richard Henderson
2021-03-09 16:20 ` [PATCH v4 65/78] target/arm: Implement SVE2 crypto destructive binary operations Richard Henderson
2021-03-09 16:20 ` [PATCH v4 66/78] target/arm: Implement SVE2 crypto constructive " Richard Henderson
2021-03-09 16:20 ` [PATCH v4 67/78] target/arm: Implement SVE2 TBL, TBX Richard Henderson
2021-03-09 16:20 ` [PATCH v4 68/78] target/arm: Implement SVE2 FCVTNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 69/78] target/arm: Implement SVE2 FCVTLT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 70/78] target/arm: Implement SVE2 FCVTXNT, FCVTX Richard Henderson
2021-03-09 16:20 ` [PATCH v4 71/78] target/arm: Implement SVE2 FLOGB Richard Henderson
2021-03-09 16:20 ` [PATCH v4 72/78] target/arm: Share table of sve load functions Richard Henderson
2021-03-09 16:20 ` [PATCH v4 73/78] target/arm: Implement SVE2 LD1RO Richard Henderson
2021-03-09 16:20 ` Richard Henderson [this message]
2021-03-09 16:20 ` [PATCH v4 75/78] target/arm: Implement SVE2 bitwise shift immediate Richard Henderson
2021-03-09 16:20 ` [PATCH v4 76/78] target/arm: Implement SVE2 fp multiply-add long Richard Henderson
2021-03-09 16:20 ` [PATCH v4 77/78] target/arm: Implement SVE2 complex integer dot product Richard Henderson
2021-03-09 16:20 ` [PATCH v4 78/78] target/arm: Enable SVE2 and some extensions Richard Henderson
2021-03-09 19:28 ` [PATCH v4 00/78] target/arm: Implement SVE2 no-reply
2021-03-10 20:17 ` Peter Maydell
2021-03-11 2:33 ` Richard Henderson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210309162041.23124-75-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=alex.bennee@linaro.org \
--cc=peter.maydell@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).