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 52/92] target/arm: Split out formats for 3 vectors + 1 index
Date: Mon, 24 May 2021 18:03:18 -0700 [thread overview]
Message-ID: <20210525010358.152808-53-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210525010358.152808-1-richard.henderson@linaro.org>
Used by FMLA and DOT, but will shortly be used more.
Split FMLA from FMLS to avoid an extra sub field;
similarly for SDOT from UDOT.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/sve.decode | 29 +++++++++++++++++++----------
target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++----------
2 files changed, 47 insertions(+), 20 deletions(-)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index a504b55dad..74ac72bdbd 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -73,6 +73,7 @@
&rprr_s rd pg rn rm s
&rprr_esz rd pg rn rm esz
&rrrr_esz rd ra rn rm esz
+&rrxr_esz rd rn rm ra index esz
&rprrr_esz rd pg rn rm ra esz
&rpri_esz rd pg rn imm esz
&ptrue rd esz pat s
@@ -252,6 +253,14 @@
@rrx_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 &rrx_esz
@rrx_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 &rrx_esz
+# Three registers and a scalar by N-bit index
+@rrxr_3 ........ .. . .. rm:3 ...... rn:5 rd:5 \
+ &rrxr_esz ra=%reg_movprfx index=%index3_22_19
+@rrxr_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 \
+ &rrxr_esz ra=%reg_movprfx
+@rrxr_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 \
+ &rrxr_esz ra=%reg_movprfx
+
###########################################################################
# Instruction patterns. Grouped according to the SVE encodingindex.xhtml.
@@ -767,10 +776,10 @@ DOT_zzzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \
ra=%reg_movprfx
# SVE integer dot product (indexed)
-DOT_zzxw 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \
- sz=0 ra=%reg_movprfx
-DOT_zzxw 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \
- sz=1 ra=%reg_movprfx
+SDOT_zzxw_s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2
+SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3
+UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2
+UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3
# SVE floating-point complex add (predicated)
FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \
@@ -789,12 +798,12 @@ FCMLA_zzxz 01100100 11 1 index:1 rm:4 0001 rot:2 rn:5 rd:5 \
### SVE FP Multiply-Add Indexed Group
# SVE floating-point multiply-add (indexed)
-FMLA_zzxz 01100100 0.1 .. rm:3 00000 sub:1 rn:5 rd:5 \
- ra=%reg_movprfx index=%index3_22_19 esz=1
-FMLA_zzxz 01100100 101 index:2 rm:3 00000 sub:1 rn:5 rd:5 \
- ra=%reg_movprfx esz=2
-FMLA_zzxz 01100100 111 index:1 rm:4 00000 sub:1 rn:5 rd:5 \
- ra=%reg_movprfx esz=3
+FMLA_zzxz 01100100 0. 1 ..... 000000 ..... ..... @rrxr_3 esz=1
+FMLA_zzxz 01100100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2
+FMLA_zzxz 01100100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3
+FMLS_zzxz 01100100 0. 1 ..... 000001 ..... ..... @rrxr_3 esz=1
+FMLS_zzxz 01100100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2
+FMLS_zzxz 01100100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3
### SVE FP Multiply Indexed Group
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 4f4b383e52..ae443f3b20 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3813,26 +3813,34 @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a)
return true;
}
-static bool trans_DOT_zzxw(DisasContext *s, arg_DOT_zzxw *a)
+static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a,
+ gen_helper_gvec_4 *fn)
{
- static gen_helper_gvec_4 * const fns[2][2] = {
- { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h },
- { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h }
- };
-
+ if (fn == NULL) {
+ return false;
+ }
if (sve_access_check(s)) {
- gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm,
- a->ra, a->index);
+ gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index);
}
return true;
}
+#define DO_RRXR(NAME, FUNC) \
+ static bool NAME(DisasContext *s, arg_rrxr_esz *a) \
+ { return do_zzxz_ool(s, a, FUNC); }
+
+DO_RRXR(trans_SDOT_zzxw_s, gen_helper_gvec_sdot_idx_b)
+DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h)
+DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b)
+DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h)
+
+#undef DO_RRXR
/*
*** SVE Floating Point Multiply-Add Indexed Group
*/
-static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
+static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub)
{
static gen_helper_gvec_4_ptr * const fns[3] = {
gen_helper_gvec_fmla_idx_h,
@@ -3847,13 +3855,23 @@ static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
vec_full_reg_offset(s, a->rn),
vec_full_reg_offset(s, a->rm),
vec_full_reg_offset(s, a->ra),
- status, vsz, vsz, (a->index << 1) | a->sub,
+ status, vsz, vsz, (a->index << 1) | sub,
fns[a->esz - 1]);
tcg_temp_free_ptr(status);
}
return true;
}
+static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
+{
+ return do_FMLA_zzxz(s, a, false);
+}
+
+static bool trans_FMLS_zzxz(DisasContext *s, arg_FMLA_zzxz *a)
+{
+ return do_FMLA_zzxz(s, a, true);
+}
+
/*
*** SVE Floating Point Multiply Indexed Group
*/
--
2.25.1
next prev parent reply other threads:[~2021-05-25 1:54 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 ` [PATCH v7 18/92] target/arm: Implement SVE2 complex integer add Richard Henderson
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 ` Richard Henderson [this message]
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=20210525010358.152808-53-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).