From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH 56/57] target/arm: Tidy SQDMULH, SQRDMULH (vector)
Date: Sun, 5 May 2024 18:04:02 -0700 [thread overview]
Message-ID: <20240506010403.6204-57-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240506010403.6204-1-richard.henderson@linaro.org>
We already have a gvec helper for the operations, but we aren't
using it on the aa32 neon side. Create a unified expander for
use by both aa32 and aa64 translators.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate.h | 4 ++++
target/arm/tcg/gengvec.c | 20 ++++++++++++++++++++
target/arm/tcg/translate-a64.c | 23 ++++-------------------
target/arm/tcg/translate-neon.c | 23 +++--------------------
4 files changed, 31 insertions(+), 39 deletions(-)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 3b1e68b779..aba21f730f 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -539,6 +539,10 @@ void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
int64_t shift, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_sqdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_sqrdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index a4133bf5f8..beedf46184 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -34,6 +34,26 @@ static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs,
opr_sz, max_sz, 0, fn);
}
+void gen_gvec_sqdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3_ptr * const fns[2] = {
+ gen_helper_neon_sqdmulh_h, gen_helper_neon_sqdmulh_s
+ };
+ tcg_debug_assert(vece >= 1 && vece <= 2);
+ gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
+}
+
+void gen_gvec_sqrdmulh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3_ptr * const fns[2] = {
+ gen_helper_neon_sqrdmulh_h, gen_helper_neon_sqrdmulh_s
+ };
+ tcg_debug_assert(vece >= 1 && vece <= 2);
+ gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]);
+}
+
void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
{
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index c217522b2b..0d8aba7a88 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -725,19 +725,6 @@ static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn,
is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
}
-/* Expand a 3-operand + qc + operation using an out-of-line helper. */
-static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn,
- int rm, gen_helper_gvec_3_ptr *fn)
-{
- TCGv_ptr qc_ptr = tcg_temp_new_ptr();
-
- tcg_gen_addi_ptr(qc_ptr, tcg_env, offsetof(CPUARMState, vfp.qc));
- tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
- vec_full_reg_offset(s, rn),
- vec_full_reg_offset(s, rm), qc_ptr,
- is_q ? 16 : 8, vec_full_reg_size(s), 0, fn);
-}
-
/* Expand a 4-operand operation using an out-of-line helper. */
static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
int rm, int ra, int data, gen_helper_gvec_4 *fn)
@@ -11001,12 +10988,10 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
switch (opcode) {
case 0x16: /* SQDMULH, SQRDMULH */
- {
- static gen_helper_gvec_3_ptr * const fns[2][2] = {
- { gen_helper_neon_sqdmulh_h, gen_helper_neon_sqrdmulh_h },
- { gen_helper_neon_sqdmulh_s, gen_helper_neon_sqrdmulh_s },
- };
- gen_gvec_op3_qc(s, is_q, rd, rn, rm, fns[size - 1][u]);
+ if (u) {
+ gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmulh_qc, size);
+ } else {
+ gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqdmulh_qc, size);
}
return;
}
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index f9a8753906..915c9e56db 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -937,28 +937,11 @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1)
}
#define DO_3SAME_VQDMULH(INSN, FUNC) \
- WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \
- WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32); \
- static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
- uint32_t rn_ofs, uint32_t rm_ofs, \
- uint32_t oprsz, uint32_t maxsz) \
- { \
- static const GVecGen3 ops[2] = { \
- { .fni4 = gen_##INSN##_tramp16 }, \
- { .fni4 = gen_##INSN##_tramp32 }, \
- }; \
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece - 1]); \
- } \
static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \
- { \
- if (a->size != 1 && a->size != 2) { \
- return false; \
- } \
- return do_3same(s, a, gen_##INSN##_3s); \
- }
+ { return a->size >= 1 && a->size <= 2 && do_3same(s, a, FUNC); }
-DO_3SAME_VQDMULH(VQDMULH, qdmulh)
-DO_3SAME_VQDMULH(VQRDMULH, qrdmulh)
+DO_3SAME_VQDMULH(VQDMULH, gen_gvec_sqdmulh_qc)
+DO_3SAME_VQDMULH(VQRDMULH, gen_gvec_sqrdmulh_qc)
#define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC) \
static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \
--
2.34.1
next prev parent reply other threads:[~2024-05-06 1:16 UTC|newest]
Thread overview: 101+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-06 1:03 [PATCH 00/57] target/arm: Convert a64 advsimd to decodetree (part 1) Richard Henderson
2024-05-06 1:03 ` [PATCH 01/57] target/arm: Split out gengvec.c Richard Henderson
2024-05-06 22:33 ` Philippe Mathieu-Daudé
2024-05-21 10:34 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 02/57] target/arm: Split out gengvec64.c Richard Henderson
2024-05-06 22:33 ` Philippe Mathieu-Daudé
2024-05-21 10:36 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 03/57] target/arm: Convert Cryptographic AES to decodetree Richard Henderson
2024-05-23 9:50 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 04/57] target/arm: Convert Cryptographic 3-register SHA " Richard Henderson
2024-05-23 10:04 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 05/57] target/arm: Convert Cryptographic 2-register " Richard Henderson
2024-05-23 10:05 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 06/57] target/arm: Convert Cryptographic 3-register SHA512 " Richard Henderson
2024-05-23 10:08 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 07/57] target/arm: Convert Cryptographic 2-register " Richard Henderson
2024-05-23 10:10 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 08/57] target/arm: Convert Cryptographic 4-register " Richard Henderson
2024-05-23 10:17 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 09/57] target/arm: Convert Cryptographic 3-register, imm2 " Richard Henderson
2024-05-23 10:19 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 10/57] target/arm: Convert XAR " Richard Henderson
2024-05-23 10:40 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 11/57] target/arm: Convert Advanced SIMD copy " Richard Henderson
2024-05-23 11:20 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 12/57] target/arm: Convert FMULX " Richard Henderson
2024-05-23 11:33 ` Peter Maydell
2024-05-23 13:00 ` Peter Maydell
2024-05-23 13:24 ` Richard Henderson
2024-05-06 1:03 ` [PATCH 13/57] target/arm: Convert FADD, FSUB, FDIV, FMUL " Richard Henderson
2024-05-23 11:37 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 14/57] target/arm: Convert FMAX, FMIN, FMAXNM, FMINNM " Richard Henderson
2024-05-23 11:38 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 15/57] target/arm: Expand vfp neg and abs inline Richard Henderson
2024-05-23 11:45 ` Peter Maydell
2024-05-23 16:29 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 16/57] target/arm: Convert FNMUL to decodetree Richard Henderson
2024-05-23 11:46 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 17/57] target/arm: Convert FMLA, FMLS " Richard Henderson
2024-05-23 12:10 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 18/57] target/arm: Convert FCMEQ, FCMGE, FCMGT, FACGE, FACGT " Richard Henderson
2024-05-23 12:15 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 19/57] target/arm: Convert FABD " Richard Henderson
2024-05-23 12:16 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 20/57] target/arm: Convert FRECPS, FRSQRTS " Richard Henderson
2024-05-23 12:19 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 21/57] target/arm: Convert FADDP " Richard Henderson
2024-05-23 12:22 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 22/57] target/arm: Convert FMAXP, FMINP, FMAXNMP, FMINNMP " Richard Henderson
2024-05-23 13:52 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 23/57] target/arm: Use gvec for neon faddp, fmaxp, fminp Richard Henderson
2024-05-23 13:55 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 24/57] target/arm: Convert ADDP to decodetree Richard Henderson
2024-05-23 13:57 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 25/57] target/arm: Use gvec for neon padd Richard Henderson
2024-05-23 13:59 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 26/57] target/arm: Convert SMAXP, SMINP, UMAXP, UMINP to decodetree Richard Henderson
2024-05-23 14:02 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 27/57] target/arm: Use gvec for neon pmax, pmin Richard Henderson
2024-05-23 14:03 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 28/57] target/arm: Convert FMLAL, FMLSL to decodetree Richard Henderson
2024-05-23 14:06 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 29/57] target/arm: Convert disas_simd_3same_logic " Richard Henderson
2024-05-23 14:08 ` Peter Maydell
2024-05-06 1:03 ` [PATCH 30/57] target/arm: Improve vector UQADD, UQSUB, SQADD, SQSUB Richard Henderson
2024-05-23 14:14 ` Peter Maydell
2024-05-23 14:51 ` Richard Henderson
2024-05-06 1:03 ` [PATCH 31/57] target/arm: Convert SUQADD and USQADD to gvec Richard Henderson
2024-05-22 10:01 ` Peter Maydell
2024-05-22 12:57 ` Richard Henderson
2024-05-06 1:03 ` [PATCH 32/57] target/arm: Inline scalar SUQADD and USQADD Richard Henderson
2024-05-21 16:46 ` Peter Maydell
2024-05-21 19:57 ` Richard Henderson
2024-05-06 1:03 ` [PATCH 33/57] target/arm: Inline scalar SQADD, UQADD, SQSUB, UQSUB Richard Henderson
2024-05-06 1:03 ` [PATCH 34/57] target/arm: Convert SQADD, SQSUB, UQADD, UQSUB to decodetree Richard Henderson
2024-05-06 1:03 ` [PATCH 35/57] target/arm: Convert SUQADD, USQADD " Richard Henderson
2024-05-06 1:03 ` [PATCH 36/57] target/arm: Convert SSHL, USHL " Richard Henderson
2024-05-06 1:03 ` [PATCH 37/57] target/arm: Convert SRSHL and URSHL (register) to gvec Richard Henderson
2024-05-06 1:03 ` [PATCH 38/57] target/arm: Convert SRSHL, URSHL to decodetree Richard Henderson
2024-05-06 1:03 ` [PATCH 39/57] target/arm: Convert SQSHL and UQSHL (register) to gvec Richard Henderson
2024-05-06 1:03 ` [PATCH 40/57] target/arm: Convert SQSHL, UQSHL to decodetree Richard Henderson
2024-05-06 1:03 ` [PATCH 41/57] target/arm: Convert SQRSHL and UQRSHL (register) to gvec Richard Henderson
2024-05-06 1:03 ` [PATCH 42/57] target/arm: Convert SQRSHL, UQRSHL to decodetree Richard Henderson
2024-05-06 1:03 ` [PATCH 43/57] target/arm: Convert ADD, SUB (vector) " Richard Henderson
2024-05-06 1:03 ` [PATCH 44/57] target/arm: Convert CMGT, CMHI, CMGE, CMHS, CMTST, CMEQ " Richard Henderson
2024-05-06 1:03 ` [PATCH 45/57] target/arm: Use TCG_COND_TSTNE in gen_cmtst_{i32,i64} Richard Henderson
2024-05-06 1:03 ` [PATCH 46/57] target/arm: Convert SHADD, UHADD to gvec Richard Henderson
2024-05-06 1:03 ` [PATCH 47/57] target/arm: Convert SHADD, UHADD to decodetree Richard Henderson
2024-05-06 1:03 ` [PATCH 48/57] target/arm: Convert SHSUB, UHSUB to gvec Richard Henderson
2024-05-06 1:03 ` [PATCH 49/57] target/arm: Convert SHSUB, UHSUB to decodetree Richard Henderson
2024-05-06 1:03 ` [PATCH 50/57] target/arm: Convert SRHADD, URHADD to gvec Richard Henderson
2024-05-06 1:03 ` [PATCH 51/57] target/arm: Convert SRHADD, URHADD to decodetree Richard Henderson
2024-05-06 1:03 ` [PATCH 52/57] target/arm: Convert SMAX, SMIN, UMAX, UMIN " Richard Henderson
2024-05-06 1:03 ` [PATCH 53/57] target/arm: Convert SABA, SABD, UABA, UABD " Richard Henderson
2024-05-06 1:04 ` [PATCH 54/57] target/arm: Convert MUL, PMUL " Richard Henderson
2024-05-06 1:04 ` [PATCH 55/57] target/arm: Convert MLA, MLS " Richard Henderson
2024-05-06 1:04 ` Richard Henderson [this message]
2024-05-06 1:04 ` [PATCH 57/57] target/arm: Convert SQDMULH, SQRDMULH " Richard Henderson
2024-05-21 16:16 ` Peter Maydell
2024-05-21 19:58 ` Richard Henderson
2024-05-23 14:19 ` [PATCH 00/57] target/arm: Convert a64 advsimd to decodetree (part 1) 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=20240506010403.6204-57-richard.henderson@linaro.org \
--to=richard.henderson@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 read-only IMAP folder(s) and NNTP newsgroup(s).