From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH 41/67] target/arm: Introduce gen_gvec_rev{16,32,64}
Date: Sun, 1 Dec 2024 09:05:40 -0600 [thread overview]
Message-ID: <20241201150607.12812-42-richard.henderson@linaro.org> (raw)
In-Reply-To: <20241201150607.12812-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate.h | 6 +++
target/arm/tcg/gengvec.c | 58 ++++++++++++++++++++++
target/arm/tcg/translate-neon.c | 88 +++++++--------------------------
3 files changed, 81 insertions(+), 71 deletions(-)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index cb8e1b2586..342ebedafc 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -586,6 +586,12 @@ void gen_gvec_cnt(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t opr_sz, uint32_t max_sz);
void gen_gvec_rbit(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_rev16(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_rev32(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_rev64(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t opr_sz, uint32_t max_sz);
/*
* Forward to the isar_feature_* tests given a DisasContext pointer.
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index 85a0b50496..33c0a94958 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -2409,3 +2409,61 @@ void gen_gvec_rbit(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0,
gen_helper_gvec_rbit_b);
}
+
+void gen_gvec_rev16(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t opr_sz, uint32_t max_sz)
+{
+ assert(vece == MO_8);
+ tcg_gen_gvec_rotli(MO_16, rd_ofs, rn_ofs, 8, opr_sz, max_sz);
+}
+
+static void gen_bswap32_i64(TCGv_i64 d, TCGv_i64 n)
+{
+ tcg_gen_bswap64_i64(d, n);
+ tcg_gen_rotli_i64(d, d, 32);
+}
+
+void gen_gvec_rev32(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t opr_sz, uint32_t max_sz)
+{
+ static const GVecGen2 g = {
+ .fni8 = gen_bswap32_i64,
+ .fni4 = tcg_gen_bswap32_i32,
+ .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+ .vece = MO_32
+ };
+
+ switch (vece) {
+ case MO_16:
+ tcg_gen_gvec_rotli(MO_32, rd_ofs, rn_ofs, 16, opr_sz, max_sz);
+ break;
+ case MO_8:
+ tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+void gen_gvec_rev64(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t opr_sz, uint32_t max_sz)
+{
+ static const GVecGen2 g[] = {
+ { .fni8 = tcg_gen_bswap64_i64,
+ .vece = MO_64 },
+ { .fni8 = tcg_gen_hswap_i64,
+ .vece = MO_64 },
+ };
+
+ switch (vece) {
+ case MO_32:
+ tcg_gen_gvec_rotli(MO_64, rd_ofs, rn_ofs, 32, opr_sz, max_sz);
+ break;
+ case MO_8:
+ case MO_16:
+ tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index 50d0bf7753..ca6f5578b4 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -2565,58 +2565,6 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a)
return true;
}
-static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
-{
- int pass, half;
- TCGv_i32 tmp[2];
-
- if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
- return false;
- }
-
- /* UNDEF accesses to D16-D31 if they don't exist. */
- if (!dc_isar_feature(aa32_simd_r32, s) &&
- ((a->vd | a->vm) & 0x10)) {
- return false;
- }
-
- if ((a->vd | a->vm) & a->q) {
- return false;
- }
-
- if (a->size == 3) {
- return false;
- }
-
- if (!vfp_access_check(s)) {
- return true;
- }
-
- tmp[0] = tcg_temp_new_i32();
- tmp[1] = tcg_temp_new_i32();
-
- for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
- for (half = 0; half < 2; half++) {
- read_neon_element32(tmp[half], a->vm, pass * 2 + half, MO_32);
- switch (a->size) {
- case 0:
- tcg_gen_bswap32_i32(tmp[half], tmp[half]);
- break;
- case 1:
- gen_swap_half(tmp[half], tmp[half]);
- break;
- case 2:
- break;
- default:
- g_assert_not_reached();
- }
- }
- write_neon_element32(tmp[1], a->vd, pass * 2, MO_32);
- write_neon_element32(tmp[0], a->vd, pass * 2 + 1, MO_32);
- }
- return true;
-}
-
static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a,
NeonGenWidenFn *widenfn,
NeonGenTwo64OpFn *opfn,
@@ -3122,6 +3070,7 @@ DO_2MISC_VEC(VCGE0, gen_gvec_cge0)
DO_2MISC_VEC(VCLT0, gen_gvec_clt0)
DO_2MISC_VEC(VCLS, gen_gvec_cls)
DO_2MISC_VEC(VCLZ, gen_gvec_clz)
+DO_2MISC_VEC(VREV64, gen_gvec_rev64)
static bool trans_VMVN(DisasContext *s, arg_2misc *a)
{
@@ -3139,6 +3088,22 @@ static bool trans_VCNT(DisasContext *s, arg_2misc *a)
return do_2misc_vec(s, a, gen_gvec_cnt);
}
+static bool trans_VREV16(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 0) {
+ return false;
+ }
+ return do_2misc_vec(s, a, gen_gvec_rev16);
+}
+
+static bool trans_VREV32(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 0 && a->size != 1) {
+ return false;
+ }
+ return do_2misc_vec(s, a, gen_gvec_rev32);
+}
+
#define WRAP_2M_3_OOL_FN(WRAPNAME, FUNC, DATA) \
static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \
uint32_t rm_ofs, uint32_t oprsz, \
@@ -3218,25 +3183,6 @@ static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn)
return true;
}
-static bool trans_VREV32(DisasContext *s, arg_2misc *a)
-{
- static NeonGenOneOpFn * const fn[] = {
- tcg_gen_bswap32_i32,
- gen_swap_half,
- NULL,
- NULL,
- };
- return do_2misc(s, a, fn[a->size]);
-}
-
-static bool trans_VREV16(DisasContext *s, arg_2misc *a)
-{
- if (a->size != 0) {
- return false;
- }
- return do_2misc(s, a, gen_rev16);
-}
-
static void gen_VABS_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
uint32_t oprsz, uint32_t maxsz)
{
--
2.43.0
next prev parent reply other threads:[~2024-12-01 15:20 UTC|newest]
Thread overview: 147+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-01 15:04 [PATCH 00/67] target/arm: AArch64 decodetree conversion, final part Richard Henderson
2024-12-01 15:05 ` [PATCH 01/67] target/arm: Use ### to separate 3rd-level sections in a64.decode Richard Henderson
2024-12-02 14:12 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 02/67] target/arm: Convert UDIV, SDIV to decodetree Richard Henderson
2024-12-02 13:49 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 03/67] target/arm: Convert LSLV, LSRV, ASRV, RORV " Richard Henderson
2024-12-02 19:31 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 04/67] target/arm: Convert CRC32, CRC32C " Richard Henderson
2024-12-02 14:01 ` Philippe Mathieu-Daudé
2024-12-02 17:49 ` Richard Henderson
2024-12-02 21:04 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 05/67] target/arm: Convert SUBP, IRG, GMI " Richard Henderson
2024-12-02 14:05 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 06/67] target/arm: Convert PACGA " Richard Henderson
2024-12-02 10:30 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 07/67] target/arm: Convert RBIT, REV16, REV32, REV64 " Richard Henderson
2024-12-05 17:22 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 08/67] target/arm: Convert CLZ, CLS " Richard Henderson
2024-12-02 14:08 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 09/67] target/arm: Convert PAC[ID]*, AUT[ID]* " Richard Henderson
2024-12-05 17:29 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 10/67] target/arm: Convert XPAC[ID] " Richard Henderson
2024-12-02 14:11 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 11/67] target/arm: Convert disas_logic_reg " Richard Henderson
2024-12-05 17:38 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 12/67] target/arm: Convert disas_add_sub_ext_reg " Richard Henderson
2024-12-05 17:42 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 13/67] target/arm: Convert disas_add_sub_reg " Richard Henderson
2024-12-05 17:45 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 14/67] target/arm: Convert disas_data_proc_3src " Richard Henderson
2024-12-05 17:55 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 15/67] target/arm: Convert disas_adc_sbc " Richard Henderson
2024-12-05 17:47 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 16/67] target/arm: Convert RMIF " Richard Henderson
2024-12-02 9:58 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 17/67] target/arm: Convert SETF8, SETF16 " Richard Henderson
2024-12-05 20:28 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 18/67] target/arm: Convert CCMP, CCMN " Richard Henderson
2024-12-05 20:32 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 19/67] target/arm: Convert disas_cond_select " Richard Henderson
2024-12-05 20:34 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 20/67] target/arm: Introduce fp_access_check_scalar_hsd Richard Henderson
2024-12-05 20:37 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 21/67] target/arm: Introduce fp_access_check_vector_hsd Richard Henderson
2024-12-05 20:37 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 22/67] target/arm: Convert FCMP, FCMPE, FCCMP, FCCMPE to decodetree Richard Henderson
2024-12-05 21:21 ` Peter Maydell
2024-12-05 21:27 ` Peter Maydell
2024-12-06 1:31 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 23/67] target/arm: Convert FMOV, FABS, FNEG (scalar) " Richard Henderson
2024-12-05 21:12 ` Peter Maydell
2024-12-06 1:52 ` Richard Henderson
2024-12-06 2:34 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 24/67] target/arm: Pass fpstatus to vfp_sqrt* Richard Henderson
2024-12-05 20:44 ` Peter Maydell
2024-12-06 2:01 ` Richard Henderson
2024-12-05 21:20 ` Philippe Mathieu-Daudé
2024-12-05 21:38 ` Peter Maydell
2024-12-05 21:40 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 25/67] target/arm: Remove helper_sqrt_f16 Richard Henderson
2024-12-04 8:51 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 26/67] target/arm: Convert FSQRT (scalar) to decodetree Richard Henderson
2024-12-06 13:19 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 27/67] target/arm: Convert FRINT[NPMSAXI] " Richard Henderson
2024-12-06 13:23 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 28/67] target/arm: Convert BFCVT " Richard Henderson
2024-12-03 14:05 ` Peter Maydell
2024-12-03 15:28 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 29/67] target/arm: Convert FRINT{32, 64}[ZX] (scalar) " Richard Henderson
2024-12-06 13:25 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 30/67] target/arm: Convert FCVT " Richard Henderson
2024-12-06 13:32 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 31/67] target/arm: Convert handle_fpfpcvt " Richard Henderson
2024-12-06 13:48 ` Peter Maydell
2024-12-06 15:10 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 32/67] target/arm: Convert FJCVTZS " Richard Henderson
2024-12-06 13:51 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 33/67] target/arm: Convert handle_fmov " Richard Henderson
2024-12-06 14:21 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 34/67] target/arm: Convert SQABS, SQNEG " Richard Henderson
2024-12-06 14:28 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 35/67] target/arm: Convert ABS, NEG " Richard Henderson
2024-12-06 14:30 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 36/67] target/arm: Introduce gen_gvec_cls, gen_gvec_clz Richard Henderson
2024-12-02 16:29 ` Philippe Mathieu-Daudé
2024-12-02 17:56 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 37/67] target/arm: Convert CLS, CLZ (vector) to decodetree Richard Henderson
2024-12-06 14:40 ` Peter Maydell
2024-12-06 15:52 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 38/67] target/arm: Introduce gen_gvec_cnt, gen_gvec_rbit Richard Henderson
2024-12-06 15:02 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 39/67] target/arm: Convert CNT, NOT, RBIT (vector) to decodetree Richard Henderson
2024-12-06 15:03 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 40/67] target/arm: Convert CMGT, CMGE, GMLT, GMLE, CMEQ (zero) " Richard Henderson
2024-12-06 15:06 ` Peter Maydell
2024-12-01 15:05 ` Richard Henderson [this message]
2024-12-06 15:09 ` [PATCH 41/67] target/arm: Introduce gen_gvec_rev{16,32,64} Peter Maydell
2024-12-01 15:05 ` [PATCH 42/67] target/arm: Convert handle_rev to decodetree Richard Henderson
2024-12-03 11:49 ` Peter Maydell
2024-12-03 14:09 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 43/67] target/arm: Move helper_neon_addlp_{s8, s16} to neon_helper.c Richard Henderson
2024-12-06 15:10 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 44/67] target/arm: Introduce gen_gvec_{s,u}{add,ada}lp Richard Henderson
2024-12-06 15:36 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 45/67] target/arm: Convert handle_2misc_pairwise to decodetree Richard Henderson
2024-12-06 15:37 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 46/67] target/arm: Remove helper_neon_{add,sub}l_u{16,32} Richard Henderson
2024-12-06 15:15 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 47/67] target/arm: Introduce clear_vec Richard Henderson
2024-12-02 16:33 ` Philippe Mathieu-Daudé
2024-12-01 15:05 ` [PATCH 48/67] target/arm: Convert XTN, SQXTUN, SQXTN, UQXTN to decodetree Richard Henderson
2024-12-06 15:46 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 49/67] target/arm: Convert FCVTN, BFCVTN " Richard Henderson
2024-12-06 15:48 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 50/67] target/arm: Convert FCVTXN " Richard Henderson
2024-12-06 15:50 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 51/67] target/arm: Convert SHLL " Richard Henderson
2024-12-06 15:52 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 52/67] target/arm: Convert FABS, FNEG (vector) " Richard Henderson
2024-12-06 16:03 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 53/67] target/arm: Convert FSQRT " Richard Henderson
2024-12-06 16:11 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 54/67] target/arm: Convert FRINT* " Richard Henderson
2024-12-06 16:12 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 55/67] target/arm: Convert FCVT* (vector, integer) scalar " Richard Henderson
2024-12-06 16:23 ` Peter Maydell
2024-12-06 18:12 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 56/67] target/arm: Convert FCVT* (vector, fixed-point) " Richard Henderson
2024-12-01 15:05 ` [PATCH 57/67] target/arm: Convert [US]CVTF (vector, integer) " Richard Henderson
2024-12-06 16:24 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 58/67] target/arm: Convert [US]CVTF (vector, fixed-point) " Richard Henderson
2024-12-06 16:27 ` Peter Maydell
2024-12-06 18:15 ` Richard Henderson
2024-12-01 15:05 ` [PATCH 59/67] target/arm: Rename helper_gvec_vcvt_[hf][su] with _rz Richard Henderson
2024-12-06 16:28 ` Peter Maydell
2024-12-01 15:05 ` [PATCH 60/67] target/arm: Convert [US]CVTF (vector) to decodetree Richard Henderson
2024-12-01 15:06 ` [PATCH 61/67] target/arm: Convert FCVTZ[SU] (vector, fixed-point) " Richard Henderson
2024-12-01 15:06 ` [PATCH 62/67] target/arm: Convert FCVT* (vector, integer) " Richard Henderson
2024-12-01 15:06 ` [PATCH 63/67] target/arm: Convert handle_2misc_fcmp_zero " Richard Henderson
2024-12-06 16:29 ` Peter Maydell
2024-12-01 15:06 ` [PATCH 64/67] target/arm: Convert FRECPE, FRECPX, FRSQRTE " Richard Henderson
2024-12-06 16:31 ` Peter Maydell
2024-12-01 15:06 ` [PATCH 65/67] target/arm: Introduce gen_gvec_urecpe, gen_gvec_ursqrte Richard Henderson
2024-12-01 15:06 ` [PATCH 66/67] target/arm: Convert URECPE and URSQRTE to decodetree Richard Henderson
2024-12-01 15:06 ` [PATCH 67/67] target/arm: Convert FCVTL " Richard Henderson
2024-12-06 16:33 ` Peter Maydell
2024-12-09 10:29 ` [PATCH 00/67] target/arm: AArch64 decodetree conversion, final part 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=20241201150607.12812-42-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 NNTP newsgroup(s).