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 19/31] target/arm: Implement SVE2 bitwise permute
Date: Thu, 26 Mar 2020 16:08:26 -0700 [thread overview]
Message-ID: <20200326230838.31112-20-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/cpu.h | 5 +++
target/arm/helper-sve.h | 15 ++++++++
target/arm/sve.decode | 6 ++++
target/arm/sve_helper.c | 73 ++++++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 36 +++++++++++++++++++
5 files changed, 135 insertions(+)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 2e9d9f046d..b7c7946771 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -3865,6 +3865,11 @@ static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id)
return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2;
}
+static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0;
+}
+
/*
* Feature tests for "does this exist in either 32-bit or 64-bit?"
*/
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 9e894a2b55..466b01986f 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2385,3 +2385,18 @@ DEF_HELPER_FLAGS_4(sve2_eoril_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_eoril_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_eoril_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_eoril_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_bext_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bext_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bext_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bext_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_bdep_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bdep_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bdep_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_bdep_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+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)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 8af35e48a5..ca60e9f2ce 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1220,3 +1220,9 @@ USHLLT 01000101 .. 0 ..... 1010 11 ..... ..... @rd_rn_tszimm_shl
EORBT 01000101 .. 0 ..... 10010 0 ..... ..... @rd_rn_rm
EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm
+
+## SVE2 bitwise permute
+
+BEXT 01000101 .. 0 ..... 1011 00 ..... ..... @rd_rn_rm
+BDEP 01000101 .. 0 ..... 1011 01 ..... ..... @rd_rn_rm
+BGRP 01000101 .. 0 ..... 1011 10 ..... ..... @rd_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 15ea1fd524..b5afa34efe 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1216,6 +1216,79 @@ DO_ZZZ_NTB(sve2_eoril_d, uint64_t, , DO_EOR)
#undef DO_ZZZ_NTB
+#define DO_BITPERM(NAME, TYPE, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \
+ TYPE nn = *(TYPE *)(vn + i); \
+ TYPE mm = *(TYPE *)(vm + i); \
+ *(TYPE *)(vd + i) = OP(nn, mm, sizeof(TYPE) * 8); \
+ } \
+}
+
+static uint64_t bitextract(uint64_t data, uint64_t mask, int n)
+{
+ uint64_t res = 0;
+ int db, rb = 0;
+
+ for (db = 0; db < n; ++db) {
+ if ((mask >> db) & 1) {
+ res |= ((data >> db) & 1) << rb;
+ ++rb;
+ }
+ }
+ return res;
+}
+
+DO_BITPERM(sve2_bext_b, uint8_t, bitextract)
+DO_BITPERM(sve2_bext_h, uint16_t, bitextract)
+DO_BITPERM(sve2_bext_s, uint32_t, bitextract)
+DO_BITPERM(sve2_bext_d, uint64_t, bitextract)
+
+static uint64_t bitdeposit(uint64_t data, uint64_t mask, int n)
+{
+ uint64_t res = 0;
+ int rb, db = 0;
+
+ for (rb = 0; rb < n; ++rb) {
+ if ((mask >> rb) & 1) {
+ res |= ((data >> db) & 1) << rb;
+ ++db;
+ }
+ }
+ return res;
+}
+
+DO_BITPERM(sve2_bdep_b, uint8_t, bitdeposit)
+DO_BITPERM(sve2_bdep_h, uint16_t, bitdeposit)
+DO_BITPERM(sve2_bdep_s, uint32_t, bitdeposit)
+DO_BITPERM(sve2_bdep_d, uint64_t, bitdeposit)
+
+static uint64_t bitgroup(uint64_t data, uint64_t mask, int n)
+{
+ uint64_t resm = 0, resu = 0;
+ int db, rbm = 0, rbu = 0;
+
+ for (db = 0; db < n; ++db) {
+ uint64_t val = (data >> db) & 1;
+ if ((mask >> db) & 1) {
+ resm |= val << rbm++;
+ } else {
+ resu |= val << rbu++;
+ }
+ }
+
+ return resm | (resu << rbm);
+}
+
+DO_BITPERM(sve2_bgrp_b, uint8_t, bitgroup)
+DO_BITPERM(sve2_bgrp_h, uint16_t, bitgroup)
+DO_BITPERM(sve2_bgrp_s, uint32_t, bitgroup)
+DO_BITPERM(sve2_bgrp_d, uint64_t, bitgroup)
+
+#undef DO_BITPERM
+
#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 3eaf9cbe51..375b9dc983 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6173,3 +6173,39 @@ static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a)
{
return do_sve2_shll_tb(s, a, true, true);
}
+
+static bool trans_BEXT(DisasContext *s, arg_rrr_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_bext_b, gen_helper_sve2_bext_h,
+ gen_helper_sve2_bext_s, gen_helper_sve2_bext_d,
+ };
+ if (!dc_isar_feature(aa64_sve2_bitperm, s)) {
+ return false;
+ }
+ return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
+}
+
+static bool trans_BDEP(DisasContext *s, arg_rrr_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h,
+ gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d,
+ };
+ if (!dc_isar_feature(aa64_sve2_bitperm, s)) {
+ return false;
+ }
+ return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
+}
+
+static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h,
+ gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d,
+ };
+ if (!dc_isar_feature(aa64_sve2_bitperm, s)) {
+ return false;
+ }
+ return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
+}
--
2.20.1
next prev parent reply other threads:[~2020-03-26 23:20 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 ` Richard Henderson [this message]
2020-03-26 23:08 ` [PATCH 20/31] target/arm: Implement SVE2 complex integer add Richard Henderson
2020-04-13 16:20 ` 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=20200326230838.31112-20-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).