From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: peter.maydell@linaro.org, qemu-arm@nongnu.org, alex.bennee@linaro.org
Subject: [PATCH v4 59/78] target/arm: Implement SVE2 saturating multiply high (indexed)
Date: Tue, 9 Mar 2021 08:20:22 -0800 [thread overview]
Message-ID: <20210309162041.23124-60-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210309162041.23124-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper.h | 14 ++++++
target/arm/sve.decode | 8 ++++
target/arm/translate-sve.c | 8 ++++
target/arm/vec_helper.c | 88 ++++++++++++++++++++++++++++++++++++++
4 files changed, 118 insertions(+)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index eb94b6b1e6..e7c463fff5 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -967,6 +967,20 @@ DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
#ifdef TARGET_AARCH64
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 8c063e77ae..31a3d909f3 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -841,6 +841,14 @@ SQDMULLB_zzx_d 01000100 .. 1 ..... 1110.0 ..... ..... @rrxl_d
SQDMULLT_zzx_s 01000100 .. 1 ..... 1110.1 ..... ..... @rrxl_s
SQDMULLT_zzx_d 01000100 .. 1 ..... 1110.1 ..... ..... @rrxl_d
+# SVE2 saturating multiply high (indexed)
+SQDMULH_zzx_h 01000100 .. 1 ..... 111100 ..... ..... @rrx_h
+SQDMULH_zzx_s 01000100 .. 1 ..... 111100 ..... ..... @rrx_s
+SQDMULH_zzx_d 01000100 .. 1 ..... 111100 ..... ..... @rrx_d
+SQRDMULH_zzx_h 01000100 .. 1 ..... 111101 ..... ..... @rrx_h
+SQRDMULH_zzx_s 01000100 .. 1 ..... 111101 ..... ..... @rrx_s
+SQRDMULH_zzx_d 01000100 .. 1 ..... 111101 ..... ..... @rrx_d
+
# SVE2 integer multiply (indexed)
MUL_zzx_h 01000100 .. 1 ..... 111110 ..... ..... @rrx_h
MUL_zzx_s 01000100 .. 1 ..... 111110 ..... ..... @rrx_s
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 27a10a9759..a3e7d4f38f 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3864,6 +3864,14 @@ DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h)
DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s)
DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
+DO_SVE2_RRX(trans_SQDMULH_zzx_h, gen_helper_sve2_sqdmulh_idx_h)
+DO_SVE2_RRX(trans_SQDMULH_zzx_s, gen_helper_sve2_sqdmulh_idx_s)
+DO_SVE2_RRX(trans_SQDMULH_zzx_d, gen_helper_sve2_sqdmulh_idx_d)
+
+DO_SVE2_RRX(trans_SQRDMULH_zzx_h, gen_helper_sve2_sqrdmulh_idx_h)
+DO_SVE2_RRX(trans_SQRDMULH_zzx_s, gen_helper_sve2_sqrdmulh_idx_s)
+DO_SVE2_RRX(trans_SQRDMULH_zzx_d, gen_helper_sve2_sqrdmulh_idx_d)
+
#undef DO_SVE2_RRX
#define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 25061c15e1..8b7269d8e1 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -240,6 +240,36 @@ void HELPER(sve2_sqrdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc)
}
}
+void HELPER(sve2_sqdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+ int16_t mm = m[i];
+ for (j = 0; j < 16 / 2; ++j) {
+ d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, &discard);
+ }
+ }
+}
+
+void HELPER(sve2_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+ int16_t mm = m[i];
+ for (j = 0; j < 16 / 2; ++j) {
+ d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, &discard);
+ }
+ }
+}
+
/* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */
int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
bool neg, bool round, uint32_t *sat)
@@ -373,6 +403,36 @@ void HELPER(sve2_sqrdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc)
}
}
+void HELPER(sve2_sqdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+ int32_t mm = m[i];
+ for (j = 0; j < 16 / 4; ++j) {
+ d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, &discard);
+ }
+ }
+}
+
+void HELPER(sve2_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+ int32_t mm = m[i];
+ for (j = 0; j < 16 / 4; ++j) {
+ d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, &discard);
+ }
+ }
+}
+
/* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */
static int64_t do_sat128_d(Int128 r)
{
@@ -452,6 +512,34 @@ void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc)
}
}
+void HELPER(sve2_sqdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx;
+
+ for (i = 0; i < opr_sz / 8; i += 16 / 8) {
+ int64_t mm = m[i];
+ for (j = 0; j < 16 / 8; ++j) {
+ d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, false);
+ }
+ }
+}
+
+void HELPER(sve2_sqrdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx;
+
+ for (i = 0; i < opr_sz / 8; i += 16 / 8) {
+ int64_t mm = m[i];
+ for (j = 0; j < 16 / 8; ++j) {
+ d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, true);
+ }
+ }
+}
+
/* Integer 8 and 16-bit dot-product.
*
* Note that for the loops herein, host endianness does not matter
--
2.25.1
next prev parent reply other threads:[~2021-03-09 18:19 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-09 16:19 [PATCH v4 00/78] target/arm: Implement SVE2 Richard Henderson
2021-03-09 16:19 ` [PATCH v4 01/78] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2 Richard Henderson
2021-03-09 16:19 ` [PATCH v4 02/78] target/arm: Implement SVE2 Integer Multiply - Unpredicated Richard Henderson
2021-03-09 16:19 ` [PATCH v4 03/78] target/arm: Implement SVE2 integer pairwise add and accumulate long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 04/78] target/arm: Implement SVE2 integer unary operations (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 05/78] target/arm: Split out saturating/rounding shifts from neon Richard Henderson
2021-03-09 16:19 ` [PATCH v4 06/78] target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 07/78] target/arm: Implement SVE2 integer halving add/subtract (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 08/78] target/arm: Implement SVE2 integer pairwise arithmetic Richard Henderson
2021-03-09 16:19 ` [PATCH v4 09/78] target/arm: Implement SVE2 saturating add/subtract (predicated) Richard Henderson
2021-03-09 16:19 ` [PATCH v4 10/78] target/arm: Implement SVE2 integer add/subtract long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 11/78] target/arm: Implement SVE2 integer add/subtract interleaved long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 12/78] target/arm: Implement SVE2 integer add/subtract wide Richard Henderson
2021-03-09 16:19 ` [PATCH v4 13/78] target/arm: Implement SVE2 integer multiply long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 14/78] target/arm: Implement PMULLB and PMULLT Richard Henderson
2021-03-09 16:19 ` [PATCH v4 15/78] target/arm: Implement SVE2 bitwise shift left long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 16/78] target/arm: Implement SVE2 bitwise exclusive-or interleaved Richard Henderson
2021-03-09 16:19 ` [PATCH v4 17/78] target/arm: Implement SVE2 bitwise permute Richard Henderson
2021-03-09 16:19 ` [PATCH v4 18/78] target/arm: Implement SVE2 complex integer add Richard Henderson
2021-03-09 16:19 ` [PATCH v4 19/78] target/arm: Implement SVE2 integer absolute difference and accumulate long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 20/78] target/arm: Implement SVE2 integer add/subtract long with carry Richard Henderson
2021-03-09 16:19 ` [PATCH v4 21/78] target/arm: Implement SVE2 bitwise shift right and accumulate Richard Henderson
2021-03-09 16:19 ` [PATCH v4 22/78] target/arm: Implement SVE2 bitwise shift and insert Richard Henderson
2021-03-09 16:19 ` [PATCH v4 23/78] target/arm: Implement SVE2 integer absolute difference and accumulate Richard Henderson
2021-03-09 16:19 ` [PATCH v4 24/78] target/arm: Implement SVE2 saturating extract narrow Richard Henderson
2021-03-09 16:19 ` [PATCH v4 25/78] target/arm: Implement SVE2 floating-point pairwise Richard Henderson
2021-03-09 16:19 ` [PATCH v4 26/78] target/arm: Implement SVE2 SHRN, RSHRN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 27/78] target/arm: Implement SVE2 SQSHRUN, SQRSHRUN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 28/78] target/arm: Implement SVE2 UQSHRN, UQRSHRN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 29/78] target/arm: Implement SVE2 SQSHRN, SQRSHRN Richard Henderson
2021-03-09 16:19 ` [PATCH v4 30/78] target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS Richard Henderson
2021-03-09 16:19 ` [PATCH v4 31/78] target/arm: Implement SVE2 WHILERW, WHILEWR Richard Henderson
2021-03-09 16:19 ` [PATCH v4 32/78] target/arm: Implement SVE2 bitwise ternary operations Richard Henderson
2021-03-09 16:19 ` [PATCH v4 33/78] target/arm: Implement SVE2 MATCH, NMATCH Richard Henderson
2021-03-09 16:19 ` [PATCH v4 34/78] target/arm: Implement SVE2 saturating multiply-add long Richard Henderson
2021-03-09 16:19 ` [PATCH v4 35/78] target/arm: Implement SVE2 saturating multiply-add high Richard Henderson
2021-03-09 16:19 ` [PATCH v4 36/78] target/arm: Implement SVE2 integer multiply-add long Richard Henderson
2021-03-09 16:20 ` [PATCH v4 37/78] target/arm: Implement SVE2 complex integer multiply-add Richard Henderson
2021-03-09 16:20 ` [PATCH v4 38/78] target/arm: Implement SVE2 ADDHNB, ADDHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 39/78] target/arm: Implement SVE2 RADDHNB, RADDHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 40/78] target/arm: Implement SVE2 SUBHNB, SUBHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 41/78] target/arm: Implement SVE2 RSUBHNB, RSUBHNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 42/78] target/arm: Implement SVE2 HISTCNT, HISTSEG Richard Henderson
2021-03-09 16:20 ` [PATCH v4 43/78] target/arm: Implement SVE2 XAR Richard Henderson
2021-03-09 16:20 ` [PATCH v4 44/78] target/arm: Implement SVE2 scatter store insns Richard Henderson
2021-03-09 16:20 ` [PATCH v4 45/78] target/arm: Implement SVE2 gather load insns Richard Henderson
2021-03-09 16:20 ` [PATCH v4 46/78] target/arm: Implement SVE2 FMMLA Richard Henderson
2021-03-09 16:20 ` [PATCH v4 47/78] target/arm: Implement SVE2 SPLICE, EXT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 48/78] target/arm: Pass separate addend to {U, S}DOT helpers Richard Henderson
2021-03-09 16:20 ` [PATCH v4 49/78] target/arm: Pass separate addend to FCMLA helpers Richard Henderson
2021-03-09 16:20 ` [PATCH v4 50/78] target/arm: Split out formats for 2 vectors + 1 index Richard Henderson
2021-03-09 16:20 ` [PATCH v4 51/78] target/arm: Split out formats for 3 " Richard Henderson
2021-03-09 16:20 ` [PATCH v4 52/78] target/arm: Implement SVE2 integer multiply (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 53/78] target/arm: Implement SVE2 integer multiply-add (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 54/78] target/arm: Implement SVE2 saturating multiply-add high (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 55/78] target/arm: Implement SVE2 saturating multiply-add (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 56/78] target/arm: Implement SVE2 integer multiply long (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 57/78] target/arm: Implement SVE2 saturating multiply (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 58/78] target/arm: Implement SVE2 signed saturating doubling multiply high Richard Henderson
2021-03-09 16:20 ` Richard Henderson [this message]
2021-03-09 16:20 ` [PATCH v4 60/78] target/arm: Implement SVE2 multiply-add long (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 61/78] target/arm: Implement SVE2 complex integer multiply-add (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 62/78] target/arm: Implement SVE mixed sign dot product (indexed) Richard Henderson
2021-03-09 16:20 ` [PATCH v4 63/78] target/arm: Implement SVE mixed sign dot product Richard Henderson
2021-03-09 16:20 ` [PATCH v4 64/78] target/arm: Implement SVE2 crypto unary operations Richard Henderson
2021-03-09 16:20 ` [PATCH v4 65/78] target/arm: Implement SVE2 crypto destructive binary operations Richard Henderson
2021-03-09 16:20 ` [PATCH v4 66/78] target/arm: Implement SVE2 crypto constructive " Richard Henderson
2021-03-09 16:20 ` [PATCH v4 67/78] target/arm: Implement SVE2 TBL, TBX Richard Henderson
2021-03-09 16:20 ` [PATCH v4 68/78] target/arm: Implement SVE2 FCVTNT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 69/78] target/arm: Implement SVE2 FCVTLT Richard Henderson
2021-03-09 16:20 ` [PATCH v4 70/78] target/arm: Implement SVE2 FCVTXNT, FCVTX Richard Henderson
2021-03-09 16:20 ` [PATCH v4 71/78] target/arm: Implement SVE2 FLOGB Richard Henderson
2021-03-09 16:20 ` [PATCH v4 72/78] target/arm: Share table of sve load functions Richard Henderson
2021-03-09 16:20 ` [PATCH v4 73/78] target/arm: Implement SVE2 LD1RO Richard Henderson
2021-03-09 16:20 ` [PATCH v4 74/78] target/arm: Implement 128-bit ZIP, UZP, TRN Richard Henderson
2021-03-09 16:20 ` [PATCH v4 75/78] target/arm: Implement SVE2 bitwise shift immediate Richard Henderson
2021-03-09 16:20 ` [PATCH v4 76/78] target/arm: Implement SVE2 fp multiply-add long Richard Henderson
2021-03-09 16:20 ` [PATCH v4 77/78] target/arm: Implement SVE2 complex integer dot product Richard Henderson
2021-03-09 16:20 ` [PATCH v4 78/78] target/arm: Enable SVE2 and some extensions Richard Henderson
2021-03-09 19:28 ` [PATCH v4 00/78] target/arm: Implement SVE2 no-reply
2021-03-10 20:17 ` Peter Maydell
2021-03-11 2:33 ` 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=20210309162041.23124-60-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=alex.bennee@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).