From: "H.J. Lu" <hjl.tools@gmail.com>
To: gcc-patches@gcc.gnu.org
Cc: Uros Bizjak <ubizjak@gmail.com>
Subject: [PATCH 02/41] i386: Emulate MMX packsswb/packssdw/packuswb with SSE2
Date: Sat, 16 Feb 2019 22:41:00 -0000 [thread overview]
Message-ID: <20190216224032.4889-3-hjl.tools@gmail.com> (raw)
In-Reply-To: <20190216224032.4889-1-hjl.tools@gmail.com>
Emulate MMX packsswb/packssdw/packuswb with SSE packsswb/packssdw/packuswb
plus moving bits 64:95 to bits 32:63 in SSE register. Only SSE register
source operand is allowed.
2019-02-08 H.J. Lu <hongjiu.lu@intel.com>
Uros Bizjak <ubizjak@gmail.com>
PR target/89021
* config/i386/i386-protos.h (ix86_move_vector_high_sse_to_mmx):
New prototype.
(ix86_split_mmx_pack): Likewise.
* config/i386/i386.c (ix86_move_vector_high_sse_to_mmx): New
function.
(ix86_split_mmx_pack): Likewise.
* config/i386/i386.md (mmx_isa): New.
(enabled): Also check mmx_isa.
* config/i386/mmx.md (any_s_truncate): New code iterator.
(s_trunsuffix): New code attr.
(mmx_packsswb): Removed.
(mmx_packssdw): Likewise.
(mmx_packuswb): Likewise.
(mmx_pack<s_trunsuffix>swb): New define_insn_and_split to emulate
MMX packsswb/packuswb with SSE2.
(mmx_packssdw): Likewise.
* config/i386/predicates.md (register_mmxmem_operand): New.
---
gcc/config/i386/i386-protos.h | 3 ++
gcc/config/i386/i386.c | 54 ++++++++++++++++++++++++++++
gcc/config/i386/i386.md | 13 +++++++
gcc/config/i386/mmx.md | 67 +++++++++++++++++++----------------
gcc/config/i386/predicates.md | 7 ++++
5 files changed, 114 insertions(+), 30 deletions(-)
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index 27f5cc13abf..a53b48438ec 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -202,6 +202,9 @@ extern void ix86_expand_vecop_qihi (enum rtx_code, rtx, rtx, rtx);
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);
+
#ifdef TREE_CODE
extern void init_cumulative_args (CUMULATIVE_ARGS *, tree, rtx, tree, int);
#endif /* TREE_CODE */
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 7d7dd80930e..d31b69d9a82 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -20221,6 +20221,60 @@ ix86_expand_vector_move_misalign (machine_mode mode, rtx operands[])
gcc_unreachable ();
}
+/* Move bits 64:95 to bits 32:63. */
+
+void
+ix86_move_vector_high_sse_to_mmx (rtx op)
+{
+ rtx mask = gen_rtx_PARALLEL (VOIDmode,
+ gen_rtvec (4, GEN_INT (0), GEN_INT (2),
+ GEN_INT (0), GEN_INT (0)));
+ rtx dest = lowpart_subreg (V4SImode, op, GET_MODE (op));
+ op = gen_rtx_VEC_SELECT (V4SImode, dest, mask);
+ rtx insn = gen_rtx_SET (dest, op);
+ emit_insn (insn);
+}
+
+/* Split MMX pack with signed/unsigned saturation with SSE/SSE2. */
+
+void
+ix86_split_mmx_pack (rtx operands[], enum rtx_code code)
+{
+ rtx op0 = operands[0];
+ rtx op1 = operands[1];
+ rtx op2 = operands[2];
+
+ machine_mode dmode = GET_MODE (op0);
+ machine_mode smode = GET_MODE (op1);
+ machine_mode inner_dmode = GET_MODE_INNER (dmode);
+ machine_mode inner_smode = GET_MODE_INNER (smode);
+
+ /* Get the corresponding SSE mode for destination. */
+ int nunits = 16 / GET_MODE_SIZE (inner_dmode);
+ machine_mode sse_dmode = mode_for_vector (GET_MODE_INNER (dmode),
+ nunits).require ();
+ machine_mode sse_half_dmode = mode_for_vector (GET_MODE_INNER (dmode),
+ nunits / 2).require ();
+
+ /* Get the corresponding SSE mode for source. */
+ nunits = 16 / GET_MODE_SIZE (inner_smode);
+ machine_mode sse_smode = mode_for_vector (GET_MODE_INNER (smode),
+ nunits).require ();
+
+ /* Generate SSE pack with signed/unsigned saturation. */
+ rtx dest = lowpart_subreg (sse_dmode, op0, GET_MODE (op0));
+ op1 = lowpart_subreg (sse_smode, op1, GET_MODE (op1));
+ op2 = lowpart_subreg (sse_smode, op2, GET_MODE (op2));
+
+ op1 = gen_rtx_fmt_e (code, sse_half_dmode, op1);
+ op2 = gen_rtx_fmt_e (code, sse_half_dmode, op2);
+ rtx insn = gen_rtx_SET (dest, gen_rtx_VEC_CONCAT (sse_dmode,
+ op1, op2));
+ emit_insn (insn);
+
+ ix86_move_vector_high_sse_to_mmx (op0);
+}
+
/* 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/i386.md b/gcc/config/i386/i386.md
index 240384917df..04ec0eeaa57 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -792,6 +792,10 @@
avx512vl,noavx512vl,x64_avx512dq,x64_avx512bw"
(const_string "base"))
+;; Define instruction set of MMX instructions
+(define_attr "mmx_isa" "base,native,x64,x64_noavx,x64_avx"
+ (const_string "base"))
+
(define_attr "enabled" ""
(cond [(eq_attr "isa" "x64") (symbol_ref "TARGET_64BIT")
(eq_attr "isa" "x64_sse2")
@@ -830,6 +834,15 @@
(eq_attr "isa" "noavx512dq") (symbol_ref "!TARGET_AVX512DQ")
(eq_attr "isa" "avx512vl") (symbol_ref "TARGET_AVX512VL")
(eq_attr "isa" "noavx512vl") (symbol_ref "!TARGET_AVX512VL")
+
+ (eq_attr "mmx_isa" "native")
+ (symbol_ref "!TARGET_MMX_WITH_SSE")
+ (eq_attr "mmx_isa" "x64")
+ (symbol_ref "TARGET_MMX_WITH_SSE")
+ (eq_attr "mmx_isa" "x64_avx")
+ (symbol_ref "TARGET_MMX_WITH_SSE && TARGET_AVX")
+ (eq_attr "mmx_isa" "x64_noavx")
+ (symbol_ref "TARGET_MMX_WITH_SSE && !TARGET_AVX")
]
(const_int 1)))
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 57060b9d233..63a390923b6 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -1021,41 +1021,48 @@
;;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-(define_insn "mmx_packsswb"
- [(set (match_operand:V8QI 0 "register_operand" "=y")
+;; Used in signed and unsigned truncations with saturation.
+(define_code_iterator any_s_truncate [ss_truncate us_truncate])
+;; Instruction suffix for truncations with saturation.
+(define_code_attr s_trunsuffix [(ss_truncate "s") (us_truncate "u")])
+
+(define_insn_and_split "mmx_pack<s_trunsuffix>swb"
+ [(set (match_operand:V8QI 0 "register_operand" "=y,x,Yv")
(vec_concat:V8QI
- (ss_truncate:V4QI
- (match_operand:V4HI 1 "register_operand" "0"))
- (ss_truncate:V4QI
- (match_operand:V4HI 2 "nonimmediate_operand" "ym"))))]
- "TARGET_MMX"
- "packsswb\t{%2, %0|%0, %2}"
- [(set_attr "type" "mmxshft")
- (set_attr "mode" "DI")])
+ (any_s_truncate:V4QI
+ (match_operand:V4HI 1 "register_operand" "0,0,Yv"))
+ (any_s_truncate:V4QI
+ (match_operand:V4HI 2 "register_mmxmem_operand" "ym,x,Yv"))))]
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ pack<s_trunsuffix>swb\t{%2, %0|%0, %2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_pack (operands, <any_s_truncate:CODE>); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxshft,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
-(define_insn "mmx_packssdw"
- [(set (match_operand:V4HI 0 "register_operand" "=y")
+(define_insn_and_split "mmx_packssdw"
+ [(set (match_operand:V4HI 0 "register_operand" "=y,x,Yv")
(vec_concat:V4HI
(ss_truncate:V2HI
- (match_operand:V2SI 1 "register_operand" "0"))
+ (match_operand:V2SI 1 "register_operand" "0,0,Yv"))
(ss_truncate:V2HI
- (match_operand:V2SI 2 "nonimmediate_operand" "ym"))))]
- "TARGET_MMX"
- "packssdw\t{%2, %0|%0, %2}"
- [(set_attr "type" "mmxshft")
- (set_attr "mode" "DI")])
-
-(define_insn "mmx_packuswb"
- [(set (match_operand:V8QI 0 "register_operand" "=y")
- (vec_concat:V8QI
- (us_truncate:V4QI
- (match_operand:V4HI 1 "register_operand" "0"))
- (us_truncate:V4QI
- (match_operand:V4HI 2 "nonimmediate_operand" "ym"))))]
- "TARGET_MMX"
- "packuswb\t{%2, %0|%0, %2}"
- [(set_attr "type" "mmxshft")
- (set_attr "mode" "DI")])
+ (match_operand:V2SI 2 "register_mmxmem_operand" "ym,x,Yv"))))]
+ "TARGET_MMX || TARGET_MMX_WITH_SSE"
+ "@
+ packssdw\t{%2, %0|%0, %2}
+ #
+ #"
+ "TARGET_MMX_WITH_SSE && reload_completed"
+ [(const_int 0)]
+ "ix86_split_mmx_pack (operands, SS_TRUNCATE); DONE;"
+ [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+ (set_attr "type" "mmxshft,sselog,sselog")
+ (set_attr "mode" "DI,TI,TI")])
(define_insn "mmx_punpckhbw"
[(set (match_operand:V8QI 0 "register_operand" "=y")
diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
index 99226e86436..f3c2f72de54 100644
--- a/gcc/config/i386/predicates.md
+++ b/gcc/config/i386/predicates.md
@@ -49,6 +49,13 @@
(and (match_code "reg")
(match_test "MMX_REGNO_P (REGNO (op))")))
+;; Match register operands, but include memory operands for
+;; !TARGET_MMX_WITH_SSE.
+(define_predicate "register_mmxmem_operand"
+ (ior (match_operand 0 "register_operand")
+ (and (not (match_test "TARGET_MMX_WITH_SSE"))
+ (match_operand 0 "memory_operand"))))
+
;; True if the operand is an SSE register.
(define_predicate "sse_reg_operand"
(and (match_code "reg")
--
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 ` [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 22:40 ` [PATCH 11/41] i386: Emulate MMX mmx_eq/mmx_gt<mode>3 " 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 12/41] i386: Emulate MMX vec_dupv2si " 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 08/41] i386: Emulate MMX ashr<mode>3/<shift_insn><mode>3 with SSE H.J. Lu
2019-02-16 22:40 ` [PATCH 03/41] i386: Emulate MMX punpcklXX/punpckhXX with SSE punpcklXX 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 22:41 ` [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 10/41] i386: Emulate MMX mmx_andnot<mode>3 with SSE 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 13/41] i386: Emulate MMX pshufw " 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 05/41] i386: Emulate MMX mulv4hi3 with SSE H.J. Lu
2019-02-16 22:41 ` [PATCH 17/41] i386: Emulate MMX mmx_pinsrw " 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 14/41] i386: Emulate MMX sse_cvtps2pi/sse_cvttps2pi " H.J. Lu
2019-02-16 22:41 ` H.J. Lu [this message]
2019-02-16 22:41 ` [PATCH 16/41] i386: Emulate MMX mmx_pextrw " H.J. Lu
2019-02-16 22:42 ` [PATCH 41/41] i386: Add tests for MMX intrinsic emulations " H.J. Lu
2019-02-16 22:46 ` [PATCH 19/41] i386: Emulate MMX mmx_pmovmskb " H.J. Lu
2019-02-16 22:46 ` [PATCH 20/41] i386: Emulate MMX mmx_umulv4hi3_highpart " H.J. Lu
2019-02-16 22:47 ` [PATCH 29/41] i386: Emulate MMX ssse3_ph<plusminus_mnemonic>dv2si3 " 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 22/41] i386: Emulate MMX mmx_uavgv8qi3 " 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 35/41] i386: Emulate MMX abs<mode>2 with SSE 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 23/41] i386: Emulate MMX mmx_uavgv4hi3 " 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 36/41] Prevent allocation of MMX registers with TARGET_MMX_WITH_SSE H.J. Lu
2019-02-18 12:56 ` Uros Bizjak
2019-02-16 22:47 ` [PATCH 38/41] i386: Allow MMX vector expanders " 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
2019-02-17 10:33 ` [PATCH 00/41] V8: Emulate MMX intrinsics with SSE 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 02/41] i386: Emulate MMX packsswb/packssdw/packuswb with SSE2 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=20190216224032.4889-3-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).