From: "H.J. Lu" <hjl.tools@gmail.com>
To: gcc-patches@gcc.gnu.org
Cc: Uros Bizjak <ubizjak@gmail.com>
Subject: [PATCH 03/41] i386: Emulate MMX punpcklXX/punpckhXX with SSE punpcklXX
Date: Sat, 16 Feb 2019 22:40:00 -0000 [thread overview]
Message-ID: <20190216224032.4889-4-hjl.tools@gmail.com> (raw)
In-Reply-To: <20190216224032.4889-1-hjl.tools@gmail.com>
Emulate MMX punpcklXX/punpckhXX with SSE punpcklXX. For MMX punpckhXX,
move bits 64:127 to bits 0:63 in SSE register. Only SSE register source
operand is allowed.
PR target/89021
* config/i386/i386-protos.h (ix86_split_mmx_punpck): New
prototype.
* config/i386/i386.c (ix86_split_mmx_punpck): New function.
* config/i386/mmx.m (mmx_punpckhbw): Changed to
define_insn_and_split to support SSE emulation.
(mmx_punpcklbw): Likewise.
(mmx_punpckhwd): Likewise.
(mmx_punpcklwd): Likewise.
(mmx_punpckhdq): Likewise.
(mmx_punpckldq): Likewise.
---
gcc/config/i386/i386-protos.h | 1 +
gcc/config/i386/i386.c | 77 +++++++++++++++++++
gcc/config/i386/mmx.md | 138 ++++++++++++++++++++++------------
3 files changed, 168 insertions(+), 48 deletions(-)
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index a53b48438ec..37581837a32 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -204,6 +204,7 @@ extern rtx ix86_split_stack_guard (void);
extern void ix86_move_vector_high_sse_to_mmx (rtx);
extern void ix86_split_mmx_pack (rtx[], enum rtx_code);
+extern void ix86_split_mmx_punpck (rtx[], bool);
#ifdef TREE_CODE
extern void init_cumulative_args (CUMULATIVE_ARGS *, tree, rtx, tree, int);
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index d31b69d9a82..a76c17beece 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -20275,6 +20275,83 @@ ix86_split_mmx_pack (rtx operands[], enum rtx_code code)
ix86_move_vector_high_sse_to_mmx (op0);
}
+/* Split MMX punpcklXX/punpckhXX with SSE punpcklXX. */
+
+void
+ix86_split_mmx_punpck (rtx operands[], bool high_p)
+{
+ rtx op0 = operands[0];
+ rtx op1 = operands[1];
+ rtx op2 = operands[2];
+ machine_mode mode = GET_MODE (op0);
+ rtx mask;
+ /* The corresponding SSE mode. */
+ machine_mode sse_mode, double_sse_mode;
+
+ switch (mode)
+ {
+ case E_V8QImode:
+ sse_mode = V16QImode;
+ double_sse_mode = V32QImode;
+ mask = gen_rtx_PARALLEL (VOIDmode,
+ gen_rtvec (16,
+ GEN_INT (0), GEN_INT (16),
+ GEN_INT (1), GEN_INT (17),
+ GEN_INT (2), GEN_INT (18),
+ GEN_INT (3), GEN_INT (19),
+ GEN_INT (4), GEN_INT (20),
+ GEN_INT (5), GEN_INT (21),
+ GEN_INT (6), GEN_INT (22),
+ GEN_INT (7), GEN_INT (23)));
+ break;
+
+ case E_V4HImode:
+ sse_mode = V8HImode;
+ double_sse_mode = V16HImode;
+ mask = gen_rtx_PARALLEL (VOIDmode,
+ gen_rtvec (8,
+ GEN_INT (0), GEN_INT (8),
+ GEN_INT (1), GEN_INT (9),
+ GEN_INT (2), GEN_INT (10),
+ GEN_INT (3), GEN_INT (11)));
+ break;
+
+ case E_V2SImode:
+ sse_mode = V4SImode;
+ double_sse_mode = V8SImode;
+ mask = gen_rtx_PARALLEL (VOIDmode,
+ gen_rtvec (4,
+ GEN_INT (0), GEN_INT (4),
+ GEN_INT (1), GEN_INT (5)));
+ break;
+
+ default:
+ gcc_unreachable ();
+ }
+
+ /* Generate SSE punpcklXX. */
+ rtx dest = lowpart_subreg (sse_mode, op0, GET_MODE (op0));
+ op1 = lowpart_subreg (sse_mode, op1, GET_MODE (op1));
+ op2 = lowpart_subreg (sse_mode, op2, GET_MODE (op2));
+
+ op1 = gen_rtx_VEC_CONCAT (double_sse_mode, op1, op2);
+ op2 = gen_rtx_VEC_SELECT (sse_mode, op1, mask);
+ rtx insn = gen_rtx_SET (dest, op2);
+ emit_insn (insn);
+
+ if (high_p)
+ {
+ /* Move bits 64:127 to bits 0:63. */
+ mask = gen_rtx_PARALLEL (VOIDmode,
+ gen_rtvec (4, GEN_INT (2), GEN_INT (3),
+ GEN_INT (0), GEN_INT (0)));
+ dest = lowpart_subreg (V4SImode, dest, GET_MODE (dest));
+ op1 = gen_rtx_VEC_SELECT (V4SImode, dest, mask);
+ insn = gen_rtx_SET (dest, op1);
+ emit_insn (insn);
+ }
+}
+
/* Helper function of ix86_fixup_binary_operands to canonicalize
operand order. Returns true if the operands should be swapped. */
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 63a390923b6..0aa793395fb 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -1064,87 +1064,129 @@
(set_attr "type" "mmxshft,sselog,sselog")
(set_attr "mode" "DI,TI,TI")])
-(define_insn "mmx_punpckhbw"
- [(set (match_operand:V8QI 0 "register_operand" "=y")
+(define_insn_and_split "mmx_punpckhbw"
+ [(set (match_operand:V8QI 0 "register_operand" "=y,x,Yv")
(vec_select:V8QI
(vec_concat:V16QI
- (match_operand:V8QI 1 "register_operand" "0")
- (match_operand:V8QI 2 "nonimmediate_operand" "ym"))
+ (match_operand:V8QI 1 "register_operand" "0,0,Yv")
+ (match_operand:V8QI 2 "register_mmxmem_operand" "ym,x,Yv"))
(parallel [(const_int 4) (const_int 12)
(const_int 5) (const_int 13)
(const_int 6) (const_int 14)
(const_int 7) (const_int 15)])))]
- "TARGET_MMX"
- "punpckhbw\t{%2, %0|%0, %2}"
- [(set_attr "type" "mmxcvt")
- (set_attr "mode" "DI")])
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ punpckhbw\t{%2, %0|%0, %2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_punpck (operands, true); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxcvt,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
-(define_insn "mmx_punpcklbw"
- [(set (match_operand:V8QI 0 "register_operand" "=y")
+(define_insn_and_split "mmx_punpcklbw"
+ [(set (match_operand:V8QI 0 "register_operand" "=y,x,Yv")
(vec_select:V8QI
(vec_concat:V16QI
- (match_operand:V8QI 1 "register_operand" "0")
- (match_operand:V8QI 2 "nonimmediate_operand" "ym"))
+ (match_operand:V8QI 1 "register_operand" "0,0,Yv")
+ (match_operand:V8QI 2 "register_mmxmem_operand" "ym,x,Yv"))
(parallel [(const_int 0) (const_int 8)
(const_int 1) (const_int 9)
(const_int 2) (const_int 10)
(const_int 3) (const_int 11)])))]
- "TARGET_MMX"
- "punpcklbw\t{%2, %0|%0, %k2}"
- [(set_attr "type" "mmxcvt")
- (set_attr "mode" "DI")])
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ punpcklbw\t{%2, %0|%0, %k2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_punpck (operands, false); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxcvt,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
-(define_insn "mmx_punpckhwd"
- [(set (match_operand:V4HI 0 "register_operand" "=y")
+(define_insn_and_split "mmx_punpckhwd"
+ [(set (match_operand:V4HI 0 "register_operand" "=y,x,Yv")
(vec_select:V4HI
(vec_concat:V8HI
- (match_operand:V4HI 1 "register_operand" "0")
- (match_operand:V4HI 2 "nonimmediate_operand" "ym"))
+ (match_operand:V4HI 1 "register_operand" "0,0,Yv")
+ (match_operand:V4HI 2 "register_mmxmem_operand" "ym,x,Yv"))
(parallel [(const_int 2) (const_int 6)
(const_int 3) (const_int 7)])))]
- "TARGET_MMX"
- "punpckhwd\t{%2, %0|%0, %2}"
- [(set_attr "type" "mmxcvt")
- (set_attr "mode" "DI")])
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ punpckhwd\t{%2, %0|%0, %2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_punpck (operands, true); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxcvt,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
-(define_insn "mmx_punpcklwd"
- [(set (match_operand:V4HI 0 "register_operand" "=y")
+(define_insn_and_split "mmx_punpcklwd"
+ [(set (match_operand:V4HI 0 "register_operand" "=y,x,Yv")
(vec_select:V4HI
(vec_concat:V8HI
- (match_operand:V4HI 1 "register_operand" "0")
- (match_operand:V4HI 2 "nonimmediate_operand" "ym"))
+ (match_operand:V4HI 1 "register_operand" "0,0,Yv")
+ (match_operand:V4HI 2 "register_mmxmem_operand" "ym,x,Yv"))
(parallel [(const_int 0) (const_int 4)
(const_int 1) (const_int 5)])))]
- "TARGET_MMX"
- "punpcklwd\t{%2, %0|%0, %k2}"
- [(set_attr "type" "mmxcvt")
- (set_attr "mode" "DI")])
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ punpcklwd\t{%2, %0|%0, %k2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_punpck (operands, false); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxcvt,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
-(define_insn "mmx_punpckhdq"
- [(set (match_operand:V2SI 0 "register_operand" "=y")
+(define_insn_and_split "mmx_punpckhdq"
+ [(set (match_operand:V2SI 0 "register_operand" "=y,x,Yv")
(vec_select:V2SI
(vec_concat:V4SI
- (match_operand:V2SI 1 "register_operand" "0")
- (match_operand:V2SI 2 "nonimmediate_operand" "ym"))
+ (match_operand:V2SI 1 "register_operand" "0,0,Yv")
+ (match_operand:V2SI 2 "register_mmxmem_operand" "ym,x,Yv"))
(parallel [(const_int 1)
(const_int 3)])))]
- "TARGET_MMX"
- "punpckhdq\t{%2, %0|%0, %2}"
- [(set_attr "type" "mmxcvt")
- (set_attr "mode" "DI")])
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ punpckhdq\t{%2, %0|%0, %2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_punpck (operands, true); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxcvt,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
-(define_insn "mmx_punpckldq"
- [(set (match_operand:V2SI 0 "register_operand" "=y")
+(define_insn_and_split "mmx_punpckldq"
+ [(set (match_operand:V2SI 0 "register_operand" "=y,x,Yv")
(vec_select:V2SI
(vec_concat:V4SI
- (match_operand:V2SI 1 "register_operand" "0")
- (match_operand:V2SI 2 "nonimmediate_operand" "ym"))
+ (match_operand:V2SI 1 "register_operand" "0,0,Yv")
+ (match_operand:V2SI 2 "register_mmxmem_operand" "ym,x,Yv"))
(parallel [(const_int 0)
(const_int 2)])))]
- "TARGET_MMX"
- "punpckldq\t{%2, %0|%0, %k2}"
- [(set_attr "type" "mmxcvt")
- (set_attr "mode" "DI")])
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ punpckldq\t{%2, %0|%0, %k2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_punpck (operands, false); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxcvt,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
(define_expand "mmx_pinsrw"
[(set (match_operand:V4HI 0 "register_operand")
--
2.20.1
next prev parent reply other threads:[~2019-02-16 22:40 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-16 22:41 [PATCH 00/41] V8: Emulate MMX intrinsics with SSE H.J. Lu
2019-02-16 22:40 ` H.J. Lu [this message]
2019-02-16 22:40 ` [PATCH 08/41] i386: Emulate MMX ashr<mode>3/<shift_insn><mode>3 " H.J. Lu
2019-02-16 22:40 ` [PATCH 01/41] i386: Allow MMX register modes in SSE registers H.J. Lu
2019-02-16 22:40 ` [PATCH 11/41] i386: Emulate MMX mmx_eq/mmx_gt<mode>3 with SSE H.J. Lu
2019-02-16 22:40 ` [PATCH 12/41] i386: Emulate MMX vec_dupv2si " H.J. Lu
2019-02-16 22:40 ` [PATCH 04/41] i386: Emulate MMX plusminus/sat_plusminus " H.J. Lu
2019-02-16 22:40 ` [PATCH 06/41] i386: Emulate MMX smulv4hi3_highpart " H.J. Lu
2019-02-16 22:40 ` [PATCH 15/41] i386: Emulate MMX sse_cvtpi2ps " H.J. Lu
2019-02-16 22:40 ` [PATCH 09/41] i386: Emulate MMX <any_logic><mode>3 " H.J. Lu
2019-02-16 22:41 ` [PATCH 16/41] i386: Emulate MMX mmx_pextrw " H.J. Lu
2019-02-16 22:41 ` [PATCH 14/41] i386: Emulate MMX sse_cvtps2pi/sse_cvttps2pi " H.J. Lu
2019-02-16 22:41 ` [PATCH 31/41] i386: Emulate MMX ssse3_pmulhrswv4hi3 " H.J. Lu
2019-02-16 22:41 ` [PATCH 02/41] i386: Emulate MMX packsswb/packssdw/packuswb with SSE2 H.J. Lu
2019-02-16 22:41 ` [PATCH 17/41] i386: Emulate MMX mmx_pinsrw with SSE H.J. Lu
2019-02-16 22:41 ` [PATCH 05/41] i386: Emulate MMX mulv4hi3 " H.J. Lu
2019-02-16 22:41 ` [PATCH 25/41] i386: Emulate MMX movntq with SSE2 movntidi H.J. Lu
2019-02-16 22:41 ` [PATCH 10/41] i386: Emulate MMX mmx_andnot<mode>3 with SSE H.J. Lu
2019-02-16 22:41 ` [PATCH 13/41] i386: Emulate MMX pshufw " H.J. Lu
2019-02-16 22:41 ` [PATCH 33/41] i386: Emulate MMX ssse3_psign<mode>3 " H.J. Lu
2019-02-16 22:41 ` [PATCH 27/41] i386: Make _mm_empty () as NOP for TARGET_MMX_WITH_SSE H.J. Lu
2019-02-17 9:45 ` Uros Bizjak
2019-02-17 13:38 ` H.J. Lu
2019-02-16 22:41 ` [PATCH 28/41] i386: Emulate MMX ssse3_ph<plusminus_mnemonic>wv4hi3 with SSE H.J. Lu
2019-02-16 22:41 ` [PATCH 07/41] i386: Emulate MMX mmx_pmaddwd " H.J. Lu
2019-02-16 22:41 ` [PATCH 40/41] i386: Enable TM MMX intrinsics with SSE2 H.J. Lu
2019-02-16 22:42 ` [PATCH 41/41] i386: Add tests for MMX intrinsic emulations with SSE H.J. Lu
2019-02-16 22:46 ` [PATCH 20/41] i386: Emulate MMX mmx_umulv4hi3_highpart " H.J. Lu
2019-02-16 22:46 ` [PATCH 19/41] i386: Emulate MMX mmx_pmovmskb " H.J. Lu
2019-02-16 22:47 ` [PATCH 38/41] i386: Allow MMX vector expanders with TARGET_MMX_WITH_SSE H.J. Lu
2019-02-17 16:25 ` Uros Bizjak
2019-02-17 17:03 ` H.J. Lu
2019-02-17 17:09 ` Uros Bizjak
2019-02-17 17:15 ` H.J. Lu
2019-02-17 17:22 ` Uros Bizjak
2019-02-17 17:28 ` H.J. Lu
2019-02-17 18:50 ` Uros Bizjak
2019-02-17 20:49 ` H.J. Lu
2019-02-16 22:47 ` [PATCH 36/41] Prevent allocation of MMX registers " H.J. Lu
2019-02-18 12:56 ` Uros Bizjak
2019-02-16 22:47 ` [PATCH 23/41] i386: Emulate MMX mmx_uavgv4hi3 with SSE H.J. Lu
2019-02-16 22:47 ` [PATCH 18/41] i386: Emulate MMX V4HI smaxmin/V8QI umaxmin " H.J. Lu
2019-02-16 22:47 ` [PATCH 30/41] i386: Emulate MMX ssse3_pmaddubsw " H.J. Lu
2019-02-16 22:47 ` [PATCH 37/41] i386: Allow MMXMODE moves with TARGET_MMX_WITH_SSE H.J. Lu
2019-02-16 22:47 ` [PATCH 39/41] i386: Allow MMX intrinsic emulation with SSE H.J. Lu
2019-02-16 22:47 ` [PATCH 24/41] i386: Emulate MMX mmx_psadbw " H.J. Lu
2019-02-16 22:47 ` [PATCH 22/41] i386: Emulate MMX mmx_uavgv8qi3 " H.J. Lu
2019-02-16 22:47 ` [PATCH 35/41] i386: Emulate MMX abs<mode>2 " H.J. Lu
2019-02-16 22:47 ` [PATCH 26/41] i386: Emulate MMX umulv1siv1di3 with SSE2 H.J. Lu
2019-02-16 22:47 ` [PATCH 32/41] i386: Emulate MMX pshufb with SSE version H.J. Lu
2019-02-16 22:47 ` [PATCH 21/41] i386: Emulate MMX maskmovq with SSE2 maskmovdqu H.J. Lu
2019-02-16 22:47 ` [PATCH 34/41] i386: Emulate MMX ssse3_palignrdi with SSE H.J. Lu
2019-02-16 22:47 ` [PATCH 29/41] i386: Emulate MMX ssse3_ph<plusminus_mnemonic>dv2si3 " H.J. Lu
2019-02-17 10:33 ` [PATCH 00/41] V8: Emulate MMX intrinsics " Uros Bizjak
2019-02-17 13:42 ` H.J. Lu
2019-02-17 15:54 ` Uros Bizjak
2019-02-17 15:57 ` Uros Bizjak
2019-02-17 17:10 ` H.J. Lu
2019-02-17 17:27 ` Uros Bizjak
2019-02-17 17:37 ` H.J. Lu
2019-02-17 18:49 ` Uros Bizjak
2019-02-17 20:47 ` H.J. Lu
2019-02-18 14:22 ` H.J. Lu
2019-02-18 14:37 ` Uros Bizjak
2019-02-18 14:48 ` H.J. Lu
2019-02-18 18:39 [PATCH 00/41] V9: " H.J. Lu
2019-02-18 18:38 ` [PATCH 03/41] i386: Emulate MMX punpcklXX/punpckhXX with SSE punpcklXX H.J. Lu
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=20190216224032.4889-4-hjl.tools@gmail.com \
--to=hjl.tools@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=ubizjak@gmail.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 read-only IMAP folder(s) and NNTP newsgroup(s).