qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
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 17/31] target/arm: Implement SVE2 bitwise shift left long
Date: Thu, 26 Mar 2020 16:08:24 -0700	[thread overview]
Message-ID: <20200326230838.31112-18-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    |  8 +++++++
 target/arm/sve.decode      |  8 +++++++
 target/arm/sve_helper.c    | 34 ++++++++++++++++++++++++++
 target/arm/translate-sve.c | 49 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 99 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 943839e2dc..9c0c41ba80 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2372,3 +2372,11 @@ DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_pmull_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sshll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sshll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sshll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_ushll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_ushll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_ushll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 440cff4597..36ef9de563 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1207,3 +1207,11 @@ SMULLB_zzz      01000101 .. 0 ..... 011 100 ..... .....  @rd_rn_rm
 SMULLT_zzz      01000101 .. 0 ..... 011 101 ..... .....  @rd_rn_rm
 UMULLB_zzz      01000101 .. 0 ..... 011 110 ..... .....  @rd_rn_rm
 UMULLT_zzz      01000101 .. 0 ..... 011 111 ..... .....  @rd_rn_rm
+
+## SVE2 bitwise shift left long
+
+# Note bit23 == 0 is handled by esz > 0 in do_sve2_shll_tb.
+SSHLLB          01000101 .. 0 ..... 1010 00 ..... .....  @rd_rn_tszimm_shl
+SSHLLT          01000101 .. 0 ..... 1010 01 ..... .....  @rd_rn_tszimm_shl
+USHLLB          01000101 .. 0 ..... 1010 10 ..... .....  @rd_rn_tszimm_shl
+USHLLT          01000101 .. 0 ..... 1010 11 ..... .....  @rd_rn_tszimm_shl
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 130697f3d9..e0a701c446 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -625,6 +625,8 @@ 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, m, 8, true, &discard); })
 #define do_uqrshl_h(n, m) \
@@ -639,6 +641,8 @@ 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
+
 #define DO_HADD_BHS(n, m)  (((int64_t)n + m) >> 1)
 #define DO_HADD_D(n, m)    ((n >> 1) + (m >> 1) + (n & m & 1))
 
@@ -1192,6 +1196,36 @@ DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t, DO_SUB)
 
 #undef DO_ZZZ_WTB
 
+#define DO_ZZI_SHLL(NAME, TYPE, TYPEN, OP) \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc)           \
+{                                                              \
+    intptr_t i, opr_sz = simd_oprsz(desc);                     \
+    int sel = (simd_data(desc) & 1) * sizeof(TYPE);            \
+    int shift = simd_data(desc) >> 1;                          \
+    for (i = 0; i < opr_sz; i += sizeof(TYPE)) {               \
+        TYPE nn = (TYPEN)(*(TYPE *)(vn + i) >> sel);           \
+        *(TYPE *)(vd + i) = OP(nn, shift);                     \
+    }                                                          \
+}
+
+#define DO_SSHLL_H(val, sh)  do_sqrshl_bhs(val, sh, 16, false, NULL)
+#define DO_SSHLL_S(val, sh)  do_sqrshl_bhs(val, sh, 32, false, NULL)
+#define DO_SSHLL_D(val, sh)  do_sqrshl_d(val, sh, false, NULL)
+
+DO_ZZI_SHLL(sve2_sshll_h, int16_t, int8_t, DO_SSHLL_H)
+DO_ZZI_SHLL(sve2_sshll_s, int32_t, int16_t, DO_SSHLL_S)
+DO_ZZI_SHLL(sve2_sshll_d, int64_t, int32_t, DO_SSHLL_D)
+
+#define DO_USHLL_H(val, sh)  do_uqrshl_bhs(val, sh, 16, false, NULL)
+#define DO_USHLL_S(val, sh)  do_uqrshl_bhs(val, sh, 32, false, NULL)
+#define DO_USHLL_D(val, sh)  do_uqrshl_d(val, sh, false, NULL)
+
+DO_ZZI_SHLL(sve2_ushll_h, uint16_t, uint8_t, DO_USHLL_H)
+DO_ZZI_SHLL(sve2_ushll_s, uint32_t, uint16_t, DO_USHLL_S)
+DO_ZZI_SHLL(sve2_ushll_d, uint64_t, uint32_t, DO_USHLL_D)
+
+#undef DO_ZZI_SHLL
+
 /* Two-operand reduction expander, controlled by a predicate.
  * The difference between TYPERED and TYPERET has to do with
  * sign-extension.  E.g. for SMAX, TYPERED must be signed,
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 67416a25ce..9873b83feb 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6105,3 +6105,52 @@ DO_SVE2_ZZZ_WTB(UADDWB, uaddw, false)
 DO_SVE2_ZZZ_WTB(UADDWT, uaddw, true)
 DO_SVE2_ZZZ_WTB(USUBWB, usubw, false)
 DO_SVE2_ZZZ_WTB(USUBWT, usubw, true)
+
+static bool do_sve2_shll_tb(DisasContext *s, arg_rri_esz *a,
+                            bool sel, bool uns)
+{
+    static gen_helper_gvec_2 * const fns[2][3] = {
+        { gen_helper_sve2_sshll_h,
+          gen_helper_sve2_sshll_s,
+          gen_helper_sve2_sshll_d },
+        { gen_helper_sve2_ushll_h,
+          gen_helper_sve2_ushll_s,
+          gen_helper_sve2_ushll_d },
+    };
+
+    if (a->esz <= 0 || !dc_isar_feature(aa64_sve2, s)) {
+        /*
+         * For < 0, invalid tsz encoding -- see tszimm_esz.
+         * For = 0, not a widening operation; note this implies bit23 = 0.
+         */
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vsz, vsz, (a->imm << 1) | sel,
+                           fns[uns][a->esz - 1]);
+    }
+    return true;
+}
+
+static bool trans_SSHLLB(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, false, false);
+}
+
+static bool trans_SSHLLT(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, true, false);
+}
+
+static bool trans_USHLLB(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, false, true);
+}
+
+static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a)
+{
+    return do_sve2_shll_tb(s, a, true, true);
+}
-- 
2.20.1



  parent reply	other threads:[~2020-03-26 23:15 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 ` Richard Henderson [this message]
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 ` [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=20200326230838.31112-18-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).