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, Stephen Long <steplong@quicinc.com>
Subject: [PATCH v4 76/78] target/arm: Implement SVE2 fp multiply-add long
Date: Tue, 9 Mar 2021 08:20:39 -0800 [thread overview]
Message-ID: <20210309162041.23124-77-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210309162041.23124-1-richard.henderson@linaro.org>
From: Stephen Long <steplong@quicinc.com>
Implements both vectored and indexed FMLALB, FMLALT, FMLSLB, FMLSLT
Signed-off-by: Stephen Long <steplong@quicinc.com>
Message-Id: <20200504171240.11220-1-steplong@quicinc.com>
[rth: Rearrange to use float16_to_float32_by_bits.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper.h | 5 +++
target/arm/sve.decode | 12 ++++++
target/arm/translate-sve.c | 75 ++++++++++++++++++++++++++++++++++++++
target/arm/vec_helper.c | 51 ++++++++++++++++++++++++++
4 files changed, 143 insertions(+)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index 86f938c938..e8b16a401f 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -987,6 +987,11 @@ DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve2_fmlal_zzzw_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve2_fmlal_zzxw_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, 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 f2a66a159a..b5c53b4c40 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1601,3 +1601,15 @@ FCVTLT_sd 01100100 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0
### SVE2 floating-point convert to integer
FLOGB 01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5 &rpr_esz
+
+### SVE2 floating-point multiply-add long (vectors)
+FMLALB_zzzw 01100100 .. 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm
+FMLALT_zzzw 01100100 .. 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm
+FMLSLB_zzzw 01100100 .. 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm
+FMLSLT_zzzw 01100100 .. 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm
+
+### SVE2 floating-point multiply-add long (indexed)
+FMLALB_zzxw 01100100 .. 1 ..... 0100.0 ..... ..... @rrxw_s
+FMLALT_zzxw 01100100 .. 1 ..... 0100.1 ..... ..... @rrxw_s
+FMLSLB_zzxw 01100100 .. 1 ..... 0110.0 ..... ..... @rrxw_s
+FMLSLT_zzxw 01100100 .. 1 ..... 0110.1 ..... ..... @rrxw_s
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 4002bc5ed4..af2c6fbb9e 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8519,3 +8519,78 @@ static bool trans_FLOGB(DisasContext *s, arg_rpr_esz *a)
}
return true;
}
+
+static bool do_FMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sub, bool sel)
+{
+ if (a->esz != MO_32 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ vec_full_reg_offset(s, a->rm),
+ vec_full_reg_offset(s, a->ra),
+ cpu_env, vsz, vsz, (sel << 1) | sub,
+ gen_helper_sve2_fmlal_zzzw_s);
+ }
+ return true;
+}
+
+static bool trans_FMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+ return do_FMLAL_zzzw(s, a, false, false);
+}
+
+static bool trans_FMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+ return do_FMLAL_zzzw(s, a, false, true);
+}
+
+static bool trans_FMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+ return do_FMLAL_zzzw(s, a, true, false);
+}
+
+static bool trans_FMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+ return do_FMLAL_zzzw(s, a, true, true);
+}
+
+static bool do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel)
+{
+ if (a->esz != MO_32 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ vec_full_reg_offset(s, a->rm),
+ vec_full_reg_offset(s, a->ra),
+ cpu_env, vsz, vsz,
+ (a->index << 2) | (sel << 1) | sub,
+ gen_helper_sve2_fmlal_zzxw_s);
+ }
+ return true;
+}
+
+static bool trans_FMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+ return do_FMLAL_zzxw(s, a, false, false);
+}
+
+static bool trans_FMLALT_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+ return do_FMLAL_zzxw(s, a, false, true);
+}
+
+static bool trans_FMLSLB_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+ return do_FMLAL_zzxw(s, a, true, false);
+}
+
+static bool trans_FMLSLT_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+ return do_FMLAL_zzxw(s, a, true, true);
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 9b2a4d5b7e..ea08b15c55 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -29,10 +29,14 @@
so addressing units smaller than that needs a host-endian fixup. */
#ifdef HOST_WORDS_BIGENDIAN
#define H1(x) ((x) ^ 7)
+#define H1_2(x) ((x) ^ 6)
+#define H1_4(x) ((x) ^ 4)
#define H2(x) ((x) ^ 3)
#define H4(x) ((x) ^ 1)
#else
#define H1(x) (x)
+#define H1_2(x) (x)
+#define H1_4(x) (x)
#define H2(x) (x)
#define H4(x) (x)
#endif
@@ -1907,6 +1911,27 @@ void HELPER(gvec_fmlal_a64)(void *vd, void *vn, void *vm,
get_flush_inputs_to_zero(&env->vfp.fp_status_f16));
}
+void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va,
+ void *venv, uint32_t desc)
+{
+ intptr_t i, oprsz = simd_oprsz(desc);
+ uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15;
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
+ CPUARMState *env = venv;
+ float_status *status = &env->vfp.fp_status;
+ bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16);
+
+ for (i = 0; i < oprsz; i += sizeof(float32)) {
+ float16 nn_16 = *(float16 *)(vn + H1_2(i + sel)) ^ negn;
+ float16 mm_16 = *(float16 *)(vm + H1_2(i + sel));
+ float32 nn = float16_to_float32_by_bits(nn_16, fz16);
+ float32 mm = float16_to_float32_by_bits(mm_16, fz16);
+ float32 aa = *(float32 *)(va + H1_4(i));
+
+ *(float32 *)(vd + H1_4(i)) = float32_muladd(nn, mm, aa, 0, status);
+ }
+}
+
static void do_fmlal_idx(float32 *d, void *vn, void *vm, float_status *fpst,
uint32_t desc, bool fz16)
{
@@ -1951,6 +1976,32 @@ void HELPER(gvec_fmlal_idx_a64)(void *vd, void *vn, void *vm,
get_flush_inputs_to_zero(&env->vfp.fp_status_f16));
}
+void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va,
+ void *venv, uint32_t desc)
+{
+ intptr_t i, j, oprsz = simd_oprsz(desc);
+ uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15;
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
+ intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16);
+ CPUARMState *env = venv;
+ float_status *status = &env->vfp.fp_status;
+ bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16);
+
+ for (i = 0; i < oprsz; i += 16) {
+ float16 mm_16 = *(float16 *)(vm + i + idx);
+ float32 mm = float16_to_float32_by_bits(mm_16, fz16);
+
+ for (j = 0; j < 16; j += sizeof(float32)) {
+ float16 nn_16 = *(float16 *)(vn + H1_2(i + j + sel)) ^ negn;
+ float32 nn = float16_to_float32_by_bits(nn_16, fz16);
+ float32 aa = *(float32 *)(va + H1_4(i + j));
+
+ *(float32 *)(vd + H1_4(i + j)) =
+ float32_muladd(nn, mm, aa, 0, status);
+ }
+ }
+}
+
void HELPER(gvec_sshl_b)(void *vd, void *vn, void *vm, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc);
--
2.25.1
next prev parent reply other threads:[~2021-03-09 18:33 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 ` [PATCH v4 59/78] target/arm: Implement SVE2 saturating multiply high (indexed) Richard Henderson
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 ` Richard Henderson [this message]
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=20210309162041.23124-77-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 \
--cc=steplong@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).