qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH 46/67] target/arm: Remove helper_neon_{add,sub}l_u{16,32}
Date: Sun,  1 Dec 2024 09:05:45 -0600	[thread overview]
Message-ID: <20241201150607.12812-47-richard.henderson@linaro.org> (raw)
In-Reply-To: <20241201150607.12812-1-richard.henderson@linaro.org>

These have generic equivalents: tcg_gen_vec_{add,sub}{16,32}_i64.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h             |  4 ----
 target/arm/tcg/neon_helper.c    | 36 ---------------------------------
 target/arm/tcg/translate-neon.c | 22 ++++++++++----------
 3 files changed, 11 insertions(+), 51 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 6369d07d05..04e422ab08 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -395,12 +395,8 @@ DEF_HELPER_1(neon_widen_s8, i64, i32)
 DEF_HELPER_1(neon_widen_u16, i64, i32)
 DEF_HELPER_1(neon_widen_s16, i64, i32)
 
-DEF_HELPER_2(neon_addl_u16, i64, i64, i64)
-DEF_HELPER_2(neon_addl_u32, i64, i64, i64)
 DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64)
 DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64)
-DEF_HELPER_2(neon_subl_u16, i64, i64, i64)
-DEF_HELPER_2(neon_subl_u32, i64, i64, i64)
 DEF_HELPER_3(neon_addl_saturate_s32, i64, env, i64, i64)
 DEF_HELPER_3(neon_addl_saturate_s64, i64, env, i64, i64)
 DEF_HELPER_2(neon_abdl_u16, i64, i32, i32)
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index 1a22857b5e..c687e882ad 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -826,24 +826,6 @@ uint64_t HELPER(neon_widen_s16)(uint32_t x)
     return ((uint32_t)(int16_t)x) | (high << 32);
 }
 
-uint64_t HELPER(neon_addl_u16)(uint64_t a, uint64_t b)
-{
-    uint64_t mask;
-    mask = (a ^ b) & 0x8000800080008000ull;
-    a &= ~0x8000800080008000ull;
-    b &= ~0x8000800080008000ull;
-    return (a + b) ^ mask;
-}
-
-uint64_t HELPER(neon_addl_u32)(uint64_t a, uint64_t b)
-{
-    uint64_t mask;
-    mask = (a ^ b) & 0x8000000080000000ull;
-    a &= ~0x8000000080000000ull;
-    b &= ~0x8000000080000000ull;
-    return (a + b) ^ mask;
-}
-
 /* Pairwise long add: add pairs of adjacent elements into
  * double-width elements in the result (eg _s8 is an 8x8->16 op)
  */
@@ -887,24 +869,6 @@ uint64_t HELPER(neon_addlp_s16)(uint64_t a)
     return (uint32_t)reslo | (((uint64_t)reshi) << 32);
 }
 
-uint64_t HELPER(neon_subl_u16)(uint64_t a, uint64_t b)
-{
-    uint64_t mask;
-    mask = (a ^ ~b) & 0x8000800080008000ull;
-    a |= 0x8000800080008000ull;
-    b &= ~0x8000800080008000ull;
-    return (a - b) ^ mask;
-}
-
-uint64_t HELPER(neon_subl_u32)(uint64_t a, uint64_t b)
-{
-    uint64_t mask;
-    mask = (a ^ ~b) & 0x8000000080000000ull;
-    a |= 0x8000000080000000ull;
-    b &= ~0x8000000080000000ull;
-    return (a - b) ^ mask;
-}
-
 uint64_t HELPER(neon_addl_saturate_s32)(CPUARMState *env, uint64_t a, uint64_t b)
 {
     uint32_t x, y;
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index 19a18018f1..0821f10fad 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -1560,8 +1560,8 @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a,
             NULL, NULL,                                                 \
         };                                                              \
         static NeonGenTwo64OpFn * const addfn[] = {                     \
-            gen_helper_neon_##OP##l_u16,                                \
-            gen_helper_neon_##OP##l_u32,                                \
+            tcg_gen_vec_##OP##16_i64,                                   \
+            tcg_gen_vec_##OP##32_i64,                                   \
             tcg_gen_##OP##_i64,                                         \
             NULL,                                                       \
         };                                                              \
@@ -1639,8 +1639,8 @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a,
     static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a)        \
     {                                                                   \
         static NeonGenTwo64OpFn * const addfn[] = {                     \
-            gen_helper_neon_##OP##l_u16,                                \
-            gen_helper_neon_##OP##l_u32,                                \
+            tcg_gen_vec_##OP##16_i64,                                   \
+            tcg_gen_vec_##OP##32_i64,                                   \
             tcg_gen_##OP##_i64,                                         \
             NULL,                                                       \
         };                                                              \
@@ -1761,8 +1761,8 @@ static bool trans_VABAL_S_3d(DisasContext *s, arg_3diff *a)
         NULL,
     };
     static NeonGenTwo64OpFn * const addfn[] = {
-        gen_helper_neon_addl_u16,
-        gen_helper_neon_addl_u32,
+        tcg_gen_vec_add16_i64,
+        tcg_gen_vec_add32_i64,
         tcg_gen_add_i64,
         NULL,
     };
@@ -1779,8 +1779,8 @@ static bool trans_VABAL_U_3d(DisasContext *s, arg_3diff *a)
         NULL,
     };
     static NeonGenTwo64OpFn * const addfn[] = {
-        gen_helper_neon_addl_u16,
-        gen_helper_neon_addl_u32,
+        tcg_gen_vec_add16_i64,
+        tcg_gen_vec_add32_i64,
         tcg_gen_add_i64,
         NULL,
     };
@@ -1840,8 +1840,8 @@ static bool trans_VMULL_U_3d(DisasContext *s, arg_3diff *a)
             NULL,                                                       \
         };                                                              \
         static NeonGenTwo64OpFn * const accfn[] = {                     \
-            gen_helper_neon_##ACC##l_u16,                               \
-            gen_helper_neon_##ACC##l_u32,                               \
+            tcg_gen_vec_##ACC##16_i64,                                  \
+            tcg_gen_vec_##ACC##32_i64,                                  \
             tcg_gen_##ACC##_i64,                                        \
             NULL,                                                       \
         };                                                              \
@@ -2371,7 +2371,7 @@ static bool trans_VMULL_U_2sc(DisasContext *s, arg_2scalar *a)
         };                                                              \
         static NeonGenTwo64OpFn * const accfn[] = {                     \
             NULL,                                                       \
-            gen_helper_neon_##ACC##l_u32,                               \
+            tcg_gen_vec_##ACC##32_i64,                                  \
             tcg_gen_##ACC##_i64,                                        \
             NULL,                                                       \
         };                                                              \
-- 
2.43.0



  parent reply	other threads:[~2024-12-01 15:15 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 ` [PATCH 41/67] target/arm: Introduce gen_gvec_rev{16,32,64} Richard Henderson
2024-12-06 15:09   ` 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 ` Richard Henderson [this message]
2024-12-06 15:15   ` [PATCH 46/67] target/arm: Remove helper_neon_{add,sub}l_u{16,32} 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=20241201150607.12812-47-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).