From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: Peter Maydell <peter.maydell@linaro.org>, qemu-arm@nongnu.org
Subject: [PATCH v7 18/92] target/arm: Implement SVE2 complex integer add
Date: Mon, 24 May 2021 18:02:44 -0700 [thread overview]
Message-ID: <20210525010358.152808-19-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210525010358.152808-1-richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Fix subtraction ordering (laurent desnogues).
---
target/arm/helper-sve.h | 10 +++++++++
target/arm/sve.decode | 9 ++++++++
target/arm/sve_helper.c | 42 ++++++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 31 ++++++++++++++++++++++++++++
4 files changed, 92 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 4861481fe0..c2155cc544 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2392,3 +2392,13 @@ DEF_HELPER_FLAGS_4(sve2_bgrp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_bgrp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_bgrp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_bgrp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_cadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_cadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_cadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_cadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqcadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqcadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqcadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqcadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 7cb89a0d47..7508b901d0 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1226,3 +1226,12 @@ EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm
BEXT 01000101 .. 0 ..... 1011 00 ..... ..... @rd_rn_rm
BDEP 01000101 .. 0 ..... 1011 01 ..... ..... @rd_rn_rm
BGRP 01000101 .. 0 ..... 1011 10 ..... ..... @rd_rn_rm
+
+#### SVE2 Accumulate
+
+## SVE2 complex integer add
+
+CADD_rot90 01000101 .. 00000 0 11011 0 ..... ..... @rdn_rm
+CADD_rot270 01000101 .. 00000 0 11011 1 ..... ..... @rdn_rm
+SQCADD_rot90 01000101 .. 00000 1 11011 0 ..... ..... @rdn_rm
+SQCADD_rot270 01000101 .. 00000 1 11011 1 ..... ..... @rdn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 3cb256e4a5..9015e68cb8 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1319,6 +1319,48 @@ DO_BITPERM(sve2_bgrp_d, uint64_t, bitgroup)
#undef DO_BITPERM
+#define DO_CADD(NAME, TYPE, H, ADD_OP, SUB_OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ int sub_r = simd_data(desc); \
+ if (sub_r) { \
+ for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \
+ TYPE acc_r = *(TYPE *)(vn + H(i)); \
+ TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE))); \
+ TYPE el2_r = *(TYPE *)(vm + H(i)); \
+ TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE))); \
+ acc_r = ADD_OP(acc_r, el2_i); \
+ acc_i = SUB_OP(acc_i, el2_r); \
+ *(TYPE *)(vd + H(i)) = acc_r; \
+ *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i; \
+ } \
+ } else { \
+ for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \
+ TYPE acc_r = *(TYPE *)(vn + H(i)); \
+ TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE))); \
+ TYPE el2_r = *(TYPE *)(vm + H(i)); \
+ TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE))); \
+ acc_r = SUB_OP(acc_r, el2_i); \
+ acc_i = ADD_OP(acc_i, el2_r); \
+ *(TYPE *)(vd + H(i)) = acc_r; \
+ *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i; \
+ } \
+ } \
+}
+
+DO_CADD(sve2_cadd_b, int8_t, H1, DO_ADD, DO_SUB)
+DO_CADD(sve2_cadd_h, int16_t, H1_2, DO_ADD, DO_SUB)
+DO_CADD(sve2_cadd_s, int32_t, H1_4, DO_ADD, DO_SUB)
+DO_CADD(sve2_cadd_d, int64_t, , DO_ADD, DO_SUB)
+
+DO_CADD(sve2_sqcadd_b, int8_t, H1, DO_SQADD_B, DO_SQSUB_B)
+DO_CADD(sve2_sqcadd_h, int16_t, H1_2, DO_SQADD_H, DO_SQSUB_H)
+DO_CADD(sve2_sqcadd_s, int32_t, H1_4, DO_SQADD_S, DO_SQSUB_S)
+DO_CADD(sve2_sqcadd_d, int64_t, , do_sqadd_d, do_sqsub_d)
+
+#undef DO_CADD
+
#define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \
void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \
{ \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 3ea42758fc..27eb6f3233 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6285,3 +6285,34 @@ static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a)
}
return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
}
+
+static bool do_cadd(DisasContext *s, arg_rrr_esz *a, bool sq, bool rot)
+{
+ static gen_helper_gvec_3 * const fns[2][4] = {
+ { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h,
+ gen_helper_sve2_cadd_s, gen_helper_sve2_cadd_d },
+ { gen_helper_sve2_sqcadd_b, gen_helper_sve2_sqcadd_h,
+ gen_helper_sve2_sqcadd_s, gen_helper_sve2_sqcadd_d },
+ };
+ return do_sve2_zzw_ool(s, a, fns[sq][a->esz], rot);
+}
+
+static bool trans_CADD_rot90(DisasContext *s, arg_rrr_esz *a)
+{
+ return do_cadd(s, a, false, false);
+}
+
+static bool trans_CADD_rot270(DisasContext *s, arg_rrr_esz *a)
+{
+ return do_cadd(s, a, false, true);
+}
+
+static bool trans_SQCADD_rot90(DisasContext *s, arg_rrr_esz *a)
+{
+ return do_cadd(s, a, true, false);
+}
+
+static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a)
+{
+ return do_cadd(s, a, true, true);
+}
--
2.25.1
next prev parent reply other threads:[~2021-05-25 1:19 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-25 1:02 [PATCH v7 00/92] target/arm: Implement SVE2 Richard Henderson
2021-05-25 1:02 ` [PATCH v7 01/92] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2 Richard Henderson
2022-07-25 7:05 ` Zenghui Yu via
2022-07-25 14:46 ` Richard Henderson
2021-05-25 1:02 ` [PATCH v7 02/92] target/arm: Implement SVE2 Integer Multiply - Unpredicated Richard Henderson
2021-05-25 1:02 ` [PATCH v7 03/92] target/arm: Implement SVE2 integer pairwise add and accumulate long Richard Henderson
2021-05-25 1:02 ` [PATCH v7 04/92] target/arm: Implement SVE2 integer unary operations (predicated) Richard Henderson
2021-05-25 1:02 ` [PATCH v7 05/92] target/arm: Split out saturating/rounding shifts from neon Richard Henderson
2021-05-25 1:02 ` [PATCH v7 06/92] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) Richard Henderson
2021-05-25 1:02 ` [PATCH v7 07/92] target/arm: Implement SVE2 integer halving add/subtract (predicated) Richard Henderson
2021-05-25 1:02 ` [PATCH v7 08/92] target/arm: Implement SVE2 integer pairwise arithmetic Richard Henderson
2021-05-25 1:02 ` [PATCH v7 09/92] target/arm: Implement SVE2 saturating add/subtract (predicated) Richard Henderson
2021-05-25 1:02 ` [PATCH v7 10/92] target/arm: Implement SVE2 integer add/subtract long Richard Henderson
2021-05-25 1:02 ` [PATCH v7 11/92] target/arm: Implement SVE2 integer add/subtract interleaved long Richard Henderson
2021-05-25 1:02 ` [PATCH v7 12/92] target/arm: Implement SVE2 integer add/subtract wide Richard Henderson
2021-05-25 1:02 ` [PATCH v7 13/92] target/arm: Implement SVE2 integer multiply long Richard Henderson
2021-05-25 1:02 ` [PATCH v7 14/92] target/arm: Implement SVE2 PMULLB, PMULLT Richard Henderson
2021-05-25 1:02 ` [PATCH v7 15/92] target/arm: Implement SVE2 bitwise shift left long Richard Henderson
2021-05-25 1:02 ` [PATCH v7 16/92] target/arm: Implement SVE2 bitwise exclusive-or interleaved Richard Henderson
2021-05-25 1:02 ` [PATCH v7 17/92] target/arm: Implement SVE2 bitwise permute Richard Henderson
2021-05-25 1:02 ` Richard Henderson [this message]
2021-05-25 1:02 ` [PATCH v7 19/92] target/arm: Implement SVE2 integer absolute difference and accumulate long Richard Henderson
2021-05-25 1:02 ` [PATCH v7 20/92] target/arm: Implement SVE2 integer add/subtract long with carry Richard Henderson
2021-05-25 1:02 ` [PATCH v7 21/92] target/arm: Implement SVE2 bitwise shift right and accumulate Richard Henderson
2021-05-25 1:02 ` [PATCH v7 22/92] target/arm: Implement SVE2 bitwise shift and insert Richard Henderson
2021-05-25 1:02 ` [PATCH v7 23/92] target/arm: Implement SVE2 integer absolute difference and accumulate Richard Henderson
2021-05-25 1:02 ` [PATCH v7 24/92] target/arm: Implement SVE2 saturating extract narrow Richard Henderson
2021-05-25 1:02 ` [PATCH v7 25/92] target/arm: Implement SVE2 floating-point pairwise Richard Henderson
2021-05-25 1:02 ` [PATCH v7 26/92] target/arm: Implement SVE2 SHRN, RSHRN Richard Henderson
2021-05-25 1:02 ` [PATCH v7 27/92] target/arm: Implement SVE2 SQSHRUN, SQRSHRUN Richard Henderson
2021-05-25 1:02 ` [PATCH v7 28/92] target/arm: Implement SVE2 UQSHRN, UQRSHRN Richard Henderson
2021-05-25 1:02 ` [PATCH v7 29/92] target/arm: Implement SVE2 SQSHRN, SQRSHRN Richard Henderson
2021-05-25 1:02 ` [PATCH v7 30/92] target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS Richard Henderson
2021-05-25 1:02 ` [PATCH v7 31/92] target/arm: Implement SVE2 WHILERW, WHILEWR Richard Henderson
2021-05-25 1:02 ` [PATCH v7 32/92] target/arm: Implement SVE2 bitwise ternary operations Richard Henderson
2021-05-25 1:02 ` [PATCH v7 33/92] target/arm: Implement SVE2 MATCH, NMATCH Richard Henderson
2021-05-25 1:03 ` [PATCH v7 34/92] target/arm: Implement SVE2 saturating multiply-add long Richard Henderson
2021-05-25 1:03 ` [PATCH v7 35/92] target/arm: Implement SVE2 saturating multiply-add high Richard Henderson
2021-05-25 1:03 ` [PATCH v7 36/92] target/arm: Implement SVE2 integer multiply-add long Richard Henderson
2021-05-25 1:03 ` [PATCH v7 37/92] target/arm: Implement SVE2 complex integer multiply-add Richard Henderson
2021-05-25 1:03 ` [PATCH v7 38/92] target/arm: Implement SVE2 ADDHNB, ADDHNT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 39/92] target/arm: Implement SVE2 RADDHNB, RADDHNT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 40/92] target/arm: Implement SVE2 SUBHNB, SUBHNT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 41/92] target/arm: Implement SVE2 RSUBHNB, RSUBHNT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 42/92] target/arm: Implement SVE2 HISTCNT, HISTSEG Richard Henderson
2021-05-25 1:03 ` [PATCH v7 43/92] target/arm: Implement SVE2 XAR Richard Henderson
2021-05-25 1:03 ` [PATCH v7 44/92] target/arm: Implement SVE2 scatter store insns Richard Henderson
2021-05-25 1:03 ` [PATCH v7 45/92] target/arm: Implement SVE2 gather load insns Richard Henderson
2021-05-25 1:03 ` [PATCH v7 46/92] target/arm: Implement SVE2 FMMLA Richard Henderson
2021-05-25 1:03 ` [PATCH v7 47/92] target/arm: Implement SVE2 SPLICE, EXT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 48/92] target/arm: Use correct output type for gvec_sdot_*_b Richard Henderson
2021-05-25 1:03 ` [PATCH v7 49/92] target/arm: Pass separate addend to {U, S}DOT helpers Richard Henderson
2021-05-25 1:03 ` [PATCH v7 50/92] target/arm: Pass separate addend to FCMLA helpers Richard Henderson
2021-05-25 1:03 ` [PATCH v7 51/92] target/arm: Split out formats for 2 vectors + 1 index Richard Henderson
2021-05-25 1:03 ` [PATCH v7 52/92] target/arm: Split out formats for 3 " Richard Henderson
2021-05-25 1:03 ` [PATCH v7 53/92] target/arm: Implement SVE2 integer multiply (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 54/92] target/arm: Implement SVE2 integer multiply-add (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 55/92] target/arm: Implement SVE2 saturating multiply-add high (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 56/92] target/arm: Implement SVE2 saturating multiply-add (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 57/92] target/arm: Implement SVE2 saturating multiply (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 58/92] target/arm: Implement SVE2 signed saturating doubling multiply high Richard Henderson
2021-05-25 1:03 ` [PATCH v7 59/92] target/arm: Implement SVE2 saturating multiply high (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 60/92] target/arm: Implement SVE2 multiply-add long (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 61/92] target/arm: Implement SVE2 integer multiply " Richard Henderson
2021-05-25 1:03 ` [PATCH v7 62/92] target/arm: Implement SVE2 complex integer multiply-add (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 63/92] target/arm: Implement SVE2 complex integer dot product Richard Henderson
2021-05-25 1:03 ` [PATCH v7 64/92] target/arm: Macroize helper_gvec_{s,u}dot_{b,h} Richard Henderson
2021-05-25 1:03 ` [PATCH v7 65/92] target/arm: Macroize helper_gvec_{s,u}dot_idx_{b,h} Richard Henderson
2021-05-25 1:03 ` [PATCH v7 66/92] target/arm: Implement SVE mixed sign dot product (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 67/92] target/arm: Implement SVE mixed sign dot product Richard Henderson
2021-05-25 1:03 ` [PATCH v7 68/92] target/arm: Implement SVE2 crypto unary operations Richard Henderson
2021-05-25 1:03 ` [PATCH v7 69/92] target/arm: Implement SVE2 crypto destructive binary operations Richard Henderson
2021-05-25 1:03 ` [PATCH v7 70/92] target/arm: Implement SVE2 crypto constructive " Richard Henderson
2021-05-25 1:03 ` [PATCH v7 71/92] target/arm: Implement SVE2 TBL, TBX Richard Henderson
2021-05-25 1:03 ` [PATCH v7 72/92] target/arm: Implement SVE2 FCVTNT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 73/92] target/arm: Implement SVE2 FCVTLT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 74/92] target/arm: Implement SVE2 FCVTXNT, FCVTX Richard Henderson
2021-05-25 1:03 ` [PATCH v7 75/92] target/arm: Implement SVE2 FLOGB Richard Henderson
2021-05-25 1:03 ` [PATCH v7 76/92] target/arm: Share table of sve load functions Richard Henderson
2021-05-25 1:03 ` [PATCH v7 77/92] target/arm: Tidy do_ldrq Richard Henderson
2021-05-25 1:03 ` [PATCH v7 78/92] target/arm: Implement SVE2 LD1RO Richard Henderson
2021-05-25 1:03 ` [PATCH v7 79/92] target/arm: Implement 128-bit ZIP, UZP, TRN Richard Henderson
2021-05-25 1:03 ` [PATCH v7 80/92] target/arm: Implement SVE2 bitwise shift immediate Richard Henderson
2021-05-25 1:03 ` [PATCH v7 81/92] target/arm: Move endian adjustment macros to vec_internal.h Richard Henderson
2021-05-25 1:03 ` [PATCH v7 82/92] target/arm: Implement SVE2 fp multiply-add long Richard Henderson
2021-05-25 1:03 ` [PATCH v7 83/92] target/arm: Implement aarch64 SUDOT, USDOT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 84/92] target/arm: Split out do_neon_ddda_fpst Richard Henderson
2021-05-25 1:03 ` [PATCH v7 85/92] target/arm: Remove unused fpst from VDOT_scalar Richard Henderson
2021-05-25 1:03 ` [PATCH v7 86/92] target/arm: Fix decode for VDOT (indexed) Richard Henderson
2021-05-25 1:03 ` [PATCH v7 87/92] target/arm: Split out do_neon_ddda Richard Henderson
2021-05-25 1:03 ` [PATCH v7 88/92] target/arm: Split decode of VSDOT and VUDOT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 89/92] target/arm: Implement aarch32 VSUDOT, VUSDOT Richard Henderson
2021-05-25 1:03 ` [PATCH v7 90/92] target/arm: Implement integer matrix multiply accumulate Richard Henderson
2021-05-25 1:03 ` [PATCH v7 91/92] linux-user/aarch64: Enable hwcap bits for sve2 and related extensions Richard Henderson
2021-05-25 1:03 ` [PATCH v7 92/92] target/arm: Enable SVE2 " Richard Henderson
2021-05-25 2:37 ` [PATCH v7 00/92] target/arm: Implement SVE2 no-reply
2021-05-25 12:33 ` Peter Maydell
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=20210525010358.152808-19-richard.henderson@linaro.org \
--to=richard.henderson@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).