From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: rajav@quicinc.com, qemu-arm@nongnu.org, apazos@quicinc.com
Subject: [PATCH 20/31] target/arm: Implement SVE2 complex integer add
Date: Thu, 26 Mar 2020 16:08:27 -0700 [thread overview]
Message-ID: <20200326230838.31112-21-richard.henderson@linaro.org> (raw)
In-Reply-To: <20200326230838.31112-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
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 466b01986f..0e4b4c48da 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2400,3 +2400,13 @@ 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 ca60e9f2ce..5fb4b5f977 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 b5afa34efe..a3653007ac 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1289,6 +1289,48 @@ 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 = 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; \
+ } \
+ } 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 = 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; \
+ } \
+ } \
+}
+
+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, TYPE, TYPEN, OP) \
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 375b9dc983..3b0aa86e79 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6209,3 +6209,34 @@ 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);
+}
--
2.20.1
next prev parent reply other threads:[~2020-03-26 23:22 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-26 23:08 [PATCH for-5.1 00/31] target/arm: SVE2, part 1 Richard Henderson
2020-03-26 23:08 ` [PATCH 01/31] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2 Richard Henderson
2020-04-11 18:45 ` Alex Bennée
2020-03-26 23:08 ` [PATCH 02/31] target/arm: Implement SVE2 Integer Multiply - Unpredicated Richard Henderson
2020-03-26 23:08 ` [PATCH 03/31] target/arm: Implement SVE2 integer pairwise add and accumulate long Richard Henderson
2020-03-26 23:08 ` [PATCH 04/31] target/arm: Remove fp_status from helper_{recpe, rsqrte}_u32 Richard Henderson
2020-03-26 23:08 ` [PATCH 05/31] target/arm: Implement SVE2 integer unary operations (predicated) Richard Henderson
2020-03-26 23:08 ` [PATCH 06/31] target/arm: Split out saturating/rounding shifts from neon Richard Henderson
2020-03-26 23:08 ` [PATCH 07/31] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) Richard Henderson
2020-03-26 23:08 ` [PATCH 08/31] target/arm: Implement SVE2 integer halving add/subtract (predicated) Richard Henderson
2020-03-26 23:08 ` [PATCH 09/31] target/arm: Implement SVE2 integer pairwise arithmetic Richard Henderson
2020-04-13 16:02 ` Laurent Desnogues
2020-03-26 23:08 ` [PATCH 10/31] target/arm: Implement SVE2 saturating add/subtract (predicated) Richard Henderson
2020-03-26 23:08 ` [PATCH 11/31] target/arm: Implement SVE2 integer add/subtract long Richard Henderson
2020-04-13 16:09 ` Laurent Desnogues
2020-03-26 23:08 ` [PATCH 12/31] target/arm: Implement SVE2 integer add/subtract interleaved long Richard Henderson
2020-03-26 23:08 ` [PATCH 13/31] target/arm: Implement SVE2 integer add/subtract wide Richard Henderson
2020-04-13 16:11 ` Laurent Desnogues
2020-03-26 23:08 ` [PATCH 14/31] target/arm: Implement SVE2 integer multiply long Richard Henderson
2020-03-26 23:08 ` [PATCH 15/31] target/arm: Implement PMULLB and PMULLT Richard Henderson
2020-03-26 23:08 ` [PATCH 16/31] target/arm: Tidy SVE tszimm shift formats Richard Henderson
2020-03-26 23:08 ` [PATCH 17/31] target/arm: Implement SVE2 bitwise shift left long Richard Henderson
2020-03-26 23:08 ` [PATCH 18/31] target/arm: Implement SVE2 bitwise exclusive-or interleaved Richard Henderson
2020-03-26 23:08 ` [PATCH 19/31] target/arm: Implement SVE2 bitwise permute Richard Henderson
2020-03-26 23:08 ` Richard Henderson [this message]
2020-04-13 16:20 ` [PATCH 20/31] target/arm: Implement SVE2 complex integer add Laurent Desnogues
2020-03-26 23:08 ` [PATCH 21/31] target/arm: Implement SVE2 integer absolute difference and accumulate long Richard Henderson
2020-04-13 16:15 ` Laurent Desnogues
2020-04-13 23:19 ` Richard Henderson
2020-04-14 7:04 ` Laurent Desnogues
2020-03-26 23:08 ` [PATCH 22/31] target/arm: Implement SVE2 integer add/subtract long with carry Richard Henderson
2020-04-13 16:18 ` Laurent Desnogues
2020-03-26 23:08 ` [PATCH 23/31] target/arm: Create arm_gen_gvec_[us]sra Richard Henderson
2020-03-26 23:08 ` [PATCH 24/31] target/arm: Create arm_gen_gvec_{u,s}{rshr,rsra} Richard Henderson
2020-03-26 23:08 ` [PATCH 25/31] target/arm: Implement SVE2 bitwise shift right and accumulate Richard Henderson
2020-03-26 23:08 ` [PATCH 26/31] target/arm: Create arm_gen_gvec_{sri,sli} Richard Henderson
2020-03-26 23:08 ` [PATCH 27/31] target/arm: Tidy handle_vec_simd_shri Richard Henderson
2020-03-26 23:08 ` [PATCH 28/31] target/arm: Implement SVE2 bitwise shift and insert Richard Henderson
2020-03-26 23:08 ` [PATCH 29/31] target/arm: Vectorize SABD/UABD Richard Henderson
2020-03-26 23:08 ` [PATCH 30/31] target/arm: Vectorize SABA/UABA Richard Henderson
2020-03-26 23:08 ` [PATCH 31/31] target/arm: Implement SVE2 integer absolute difference and accumulate Richard Henderson
2020-04-01 21:17 ` [PATCH for-5.1 00/31] target/arm: SVE2, part 1 Ana Pazos
2020-04-22 2:51 ` LIU Zhiwei
2020-04-22 2:55 ` 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=20200326230838.31112-21-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=apazos@quicinc.com \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=rajav@quicinc.com \
/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).