Hello!
Attached patch improves zero_extend patterns by:
- removing flags reg clobber from zero_extendsidi patterns for 32bit
targets. Everything, including "movl $0, mem" can be split without
using flags reg clobber.
- removing intermediate *zero_extend*2_movzbl_and patterns. We do not
need to remove any fake clobbers in !TARGET_ZERO_EXTEND_WITH_AND case
anymore
- adding o,0 and x,x register alternatives. We can split matching
memory to load 0 in highpart for 64bit and 32bit targets, and movd
zero extends also in xmm->xmm case
- truly splitting "and" RTXes to zero_extend RTXes when appropriate
(but only in !TARGET_ZERO_EXTEND_WITH_AND case), again removing
unneeded flags reg clobbers
- fixing TARGET_ZERO_EXTEND_WITH_AND peephole2
2012-03-04 Uros Bizjak <ubiz...@gmail.com>
* config/i386/constraints.md (Ya): New internal constraint.
* config/i386/i386.md (zero_extendsidi2): Remove expansion.
(*zero_extendsidi2_rex64): Add x,x alternative.
(*zero_extendsidi2): Ditto. Add o,0 alternative.
Remove flags reg clobber. Adjust corresponding splits.
(zero_extend<mode>si2): Macroize expander from zero_extendhisi2 and
zero_extendqisi2 expanders using SWI12 mode iterator.
(zero_extend<mode>si2_and): Macroize insn from
zero_extendhisi2_and and zero_extendqisi2_and. Merge corresponding
splitters.
(*zero_extend<mode>si2): Macroize insn from
*zero_extendhisi2_movzbl and *zero_extendqisi2_movzbl.
(*zero_extend*2_movzbl_and): Remove insn patterns.
(zero_extendqihi2_and): Merge corresponding splitter.
(*zero_extendqihi2): Rename from *zero_extendqihi2_movzbl.
(*zero_extend*2_movzbl_and): Remove insn patterns.
(*anddi_1): Split TYPE_IMOVX instructions.
(*andsi_1): Use Ya for alternative 2. Split TYPE_IMOVX instructions.
(*andhi_1): Ditto.
(and->zext splitter): Add splitter pattern.
(zero extend with andsi3 splitter): Adjust zero_extend pattern.
Patch was tested on x86_64-pc-linux-gnu {,-m32} and committed to mainline SVN.
Uros.
Index: config/i386/constraints.md
===================================================================
--- config/i386/constraints.md (revision 184886)
+++ config/i386/constraints.md (working copy)
@@ -89,6 +89,7 @@
;; z First SSE register.
;; i SSE2 inter-unit moves enabled
;; m MMX inter-unit moves enabled
+;; a Integer register when zero extensions with AND are disabled
;; p Integer register when TARGET_PARTIAL_REG_STALL is disabled
;; d Integer register when integer DFmode moves are enabled
;; x Integer register when integer XFmode moves are enabled
@@ -108,6 +109,11 @@
"TARGET_PARTIAL_REG_STALL ? NO_REGS : GENERAL_REGS"
"@internal Any integer register when TARGET_PARTIAL_REG_STALL is disabled.")
+(define_register_constraint "Ya"
+ "TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun)
+ ? NO_REGS : GENERAL_REGS"
+ "@internal Any integer register when zero extensions with AND are disabled.")
+
(define_register_constraint "Yd"
"(TARGET_64BIT
|| (TARGET_INTEGER_DFMODE_MOVES && optimize_function_for_speed_p (cfun)))
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md (revision 184886)
+++ config/i386/i386.md (working copy)
@@ -3371,20 +3371,14 @@
(define_expand "zero_extendsidi2"
[(set (match_operand:DI 0 "nonimmediate_operand" "")
- (zero_extend:DI (match_operand:SI 1 "nonimmediate_operand" "")))]
- ""
-{
- if (!TARGET_64BIT)
- {
- emit_insn (gen_zero_extendsidi2_1 (operands[0], operands[1]));
- DONE;
- }
-})
+ (zero_extend:DI (match_operand:SI 1 "nonimmediate_operand" "")))])
(define_insn "*zero_extendsidi2_rex64"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,o,?*Ym,?*y,?*Yi,*x")
+ [(set (match_operand:DI 0 "nonimmediate_operand"
+ "=r,o,?*Ym,?*y,?*Yi,!*x")
(zero_extend:DI
- (match_operand:SI 1 "nonimmediate_operand" "rm,0,r ,m ,r ,m")))]
+ (match_operand:SI 1 "nonimmediate_operand"
+ "rm,0,r ,m ,r ,m*x")))]
"TARGET_64BIT"
"@
mov{l}\t{%1, %k0|%k0, %1}
@@ -3393,24 +3387,17 @@
movd\t{%1, %0|%0, %1}
%vmovd\t{%1, %0|%0, %1}
%vmovd\t{%1, %0|%0, %1}"
- [(set_attr "type" "imovx,imov,mmxmov,mmxmov,ssemov,ssemov")
+ [(set_attr "isa" "*,*,*,*,*,sse2")
+ (set_attr "type" "imovx,multi,mmxmov,mmxmov,ssemov,ssemov")
(set_attr "prefix" "orig,*,orig,orig,maybe_vex,maybe_vex")
(set_attr "prefix_0f" "0,*,*,*,*,*")
- (set_attr "mode" "SI,DI,DI,DI,TI,TI")])
+ (set_attr "mode" "SI,SI,DI,DI,TI,TI")])
-(define_split
- [(set (match_operand:DI 0 "memory_operand" "")
- (zero_extend:DI (match_dup 0)))]
- "TARGET_64BIT"
- [(set (match_dup 4) (const_int 0))]
- "split_double_mode (DImode, &operands[0], 1, &operands[3], &operands[4]);")
-
-;; %%% Kill me once multi-word ops are sane.
-(define_insn "zero_extendsidi2_1"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,?r,?o,?*Ym,?*y,?*Yi,*x")
- (zero_extend:DI
- (match_operand:SI 1 "nonimmediate_operand" "0,rm,r ,r ,m ,r ,m")))
- (clobber (reg:CC FLAGS_REG))]
+(define_insn "*zero_extendsidi2"
+ [(set (match_operand:DI 0 "nonimmediate_operand"
+ "=ro,?r,?o,?*Ym,?*y,?*Yi,!*x")
+ (zero_extend:DI (match_operand:SI 1 "nonimmediate_operand"
+ "0 ,rm,r ,r ,m ,r ,m*x")))]
"!TARGET_64BIT"
"@
#
@@ -3426,19 +3413,26 @@
(set_attr "mode" "SI,SI,SI,DI,DI,TI,TI")])
(define_split
+ [(set (match_operand:DI 0 "memory_operand" "")
+ (zero_extend:DI (match_operand:SI 1 "memory_operand" "")))]
+ "reload_completed"
+ [(set (match_dup 4) (const_int 0))]
+ "split_double_mode (DImode, &operands[0], 1, &operands[3], &operands[4]);")
+
+(define_split
[(set (match_operand:DI 0 "register_operand" "")
- (zero_extend:DI (match_operand:SI 1 "register_operand" "")))
- (clobber (reg:CC FLAGS_REG))]
+ (zero_extend:DI (match_operand:SI 1 "register_operand" "")))]
"!TARGET_64BIT && reload_completed
+ && !(MMX_REG_P (operands[0]) || SSE_REG_P (operands[0]))
&& true_regnum (operands[0]) == true_regnum (operands[1])"
[(set (match_dup 4) (const_int 0))]
"split_double_mode (DImode, &operands[0], 1, &operands[3], &operands[4]);")
(define_split
[(set (match_operand:DI 0 "nonimmediate_operand" "")
- (zero_extend:DI (match_operand:SI 1 "general_operand" "")))
- (clobber (reg:CC FLAGS_REG))]
+ (zero_extend:DI (match_operand:SI 1 "nonimmediate_operand" "")))]
"!TARGET_64BIT && reload_completed
+ && !(MEM_P (operands[0]) && MEM_P (operands[1]))
&& !(MMX_REG_P (operands[0]) || SSE_REG_P (operands[0]))"
[(set (match_dup 3) (match_dup 1))
(set (match_dup 4) (const_int 0))]
@@ -3453,112 +3447,100 @@
[(set_attr "type" "imovx")
(set_attr "mode" "SI")])
-(define_expand "zero_extendhisi2"
+(define_expand "zero_extend<mode>si2"
[(set (match_operand:SI 0 "register_operand" "")
- (zero_extend:SI (match_operand:HI 1 "nonimmediate_operand" "")))]
+ (zero_extend:SI (match_operand:SWI12 1 "nonimmediate_operand" "")))]
""
{
if (TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))
{
- operands[1] = force_reg (HImode, operands[1]);
- emit_insn (gen_zero_extendhisi2_and (operands[0], operands[1]));
+ operands[1] = force_reg (<MODE>mode, operands[1]);
+ emit_insn (gen_zero_extend<mode>si2_and (operands[0], operands[1]));
DONE;
}
})
-(define_insn_and_split "zero_extendhisi2_and"
- [(set (match_operand:SI 0 "register_operand" "=r")
- (zero_extend:SI (match_operand:HI 1 "register_operand" "0")))
+(define_insn_and_split "zero_extend<mode>si2_and"
+ [(set (match_operand:SI 0 "register_operand" "=r,?&<r>")
+ (zero_extend:SI
+ (match_operand:SWI12 1 "nonimmediate_operand" "0,<r>m")))
(clobber (reg:CC FLAGS_REG))]
"TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun)"
"#"
"&& reload_completed"
- [(parallel [(set (match_dup 0) (and:SI (match_dup 0) (const_int 65535)))
+ [(parallel [(set (match_dup 0) (and:SI (match_dup 0) (match_dup 2)))
(clobber (reg:CC FLAGS_REG))])]
- ""
+{
+ if (true_regnum (operands[0]) != true_regnum (operands[1]))
+ {
+ ix86_expand_clear (operands[0]);
+
+ gcc_assert (!TARGET_PARTIAL_REG_STALL);
+ emit_insn (gen_movstrict<mode>
+ (gen_lowpart (<MODE>mode, operands[0]), operands[1]));
+ DONE;
+ }
+
+ operands[2] = GEN_INT (GET_MODE_MASK (<MODE>mode));
+}
[(set_attr "type" "alu1")
(set_attr "mode" "SI")])
-(define_insn "*zero_extendhisi2_movzwl"
+(define_insn "*zero_extend<mode>si2"
[(set (match_operand:SI 0 "register_operand" "=r")
- (zero_extend:SI (match_operand:HI 1 "nonimmediate_operand" "rm")))]
- "!TARGET_ZERO_EXTEND_WITH_AND
- || optimize_function_for_size_p (cfun)"
- "movz{wl|x}\t{%1, %0|%0, %1}"
+ (zero_extend:SI
+ (match_operand:SWI12 1 "nonimmediate_operand" "<r>m")))]
+ "!(TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))"
+ "movz{<imodesuffix>l|x}\t{%1, %0|%0, %1}"
[(set_attr "type" "imovx")
(set_attr "mode" "SI")])
-(define_expand "zero_extendqi<mode>2"
- [(parallel
- [(set (match_operand:SWI24 0 "register_operand" "")
- (zero_extend:SWI24 (match_operand:QI 1 "nonimmediate_operand" "")))
- (clobber (reg:CC FLAGS_REG))])])
+(define_expand "zero_extendqihi2"
+ [(set (match_operand:HI 0 "register_operand" "")
+ (zero_extend:HI (match_operand:QI 1 "nonimmediate_operand" "")))]
+ ""
+{
+ if (TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))
+ {
+ operands[1] = force_reg (QImode, operands[1]);
+ emit_insn (gen_zero_extendqihi2_and (operands[0], operands[1]));
+ DONE;
+ }
+})
-(define_insn "*zero_extendqi<mode>2_and"
- [(set (match_operand:SWI24 0 "register_operand" "=r,?&q")
- (zero_extend:SWI24 (match_operand:QI 1 "nonimmediate_operand" "0,qm")))
+(define_insn_and_split "zero_extendqihi2_and"
+ [(set (match_operand:HI 0 "register_operand" "=r,?&q")
+ (zero_extend:HI (match_operand:QI 1 "nonimmediate_operand" "0,qm")))
(clobber (reg:CC FLAGS_REG))]
"TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun)"
"#"
- [(set_attr "type" "alu1")
- (set_attr "mode" "<MODE>")])
-
-;; When source and destination does not overlap, clear destination
-;; first and then do the movb
-(define_split
- [(set (match_operand:SWI24 0 "register_operand" "")
- (zero_extend:SWI24 (match_operand:QI 1 "nonimmediate_operand" "")))
- (clobber (reg:CC FLAGS_REG))]
- "reload_completed
- && (TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))
- && ANY_QI_REG_P (operands[0])
- && (ANY_QI_REG_P (operands[1]) || MEM_P (operands[1]))
- && !reg_overlap_mentioned_p (operands[0], operands[1])"
- [(set (strict_low_part (match_dup 2)) (match_dup 1))]
+ "&& reload_completed"
+ [(parallel [(set (match_dup 0) (and:SI (match_dup 0) (const_int 255)))
+ (clobber (reg:CC FLAGS_REG))])]
{
- operands[2] = gen_lowpart (QImode, operands[0]);
- ix86_expand_clear (operands[0]);
-})
+ if (true_regnum (operands[0]) != true_regnum (operands[1]))
+ {
+ ix86_expand_clear (operands[0]);
-(define_insn "*zero_extendqi<mode>2_movzbl_and"
- [(set (match_operand:SWI24 0 "register_operand" "=r,r")
- (zero_extend:SWI24 (match_operand:QI 1 "nonimmediate_operand" "qm,0")))
- (clobber (reg:CC FLAGS_REG))]
- "!TARGET_ZERO_EXTEND_WITH_AND || optimize_function_for_size_p (cfun)"
- "#"
- [(set_attr "type" "imovx,alu1")
- (set_attr "mode" "<MODE>")])
+ gcc_assert (!TARGET_PARTIAL_REG_STALL);
+ emit_insn (gen_movstrictqi
+ (gen_lowpart (QImode, operands[0]), operands[1]));
+ DONE;
+ }
-;; For the movzbl case strip only the clobber
-(define_split
- [(set (match_operand:SWI24 0 "register_operand" "")
- (zero_extend:SWI24 (match_operand:QI 1 "nonimmediate_operand" "")))
- (clobber (reg:CC FLAGS_REG))]
- "reload_completed
- && (!TARGET_ZERO_EXTEND_WITH_AND || optimize_function_for_size_p (cfun))
- && (!REG_P (operands[1]) || ANY_QI_REG_P (operands[1]))"
- [(set (match_dup 0)
- (zero_extend:SWI24 (match_dup 1)))])
+ operands[0] = gen_lowpart (SImode, operands[0]);
+}
+ [(set_attr "type" "alu1")
+ (set_attr "mode" "SI")])
; zero extend to SImode to avoid partial register stalls
-(define_insn "*zero_extendqi<mode>2_movzbl"
- [(set (match_operand:SWI24 0 "register_operand" "=r")
- (zero_extend:SWI24 (match_operand:QI 1 "nonimmediate_operand" "qm")))]
- "reload_completed
- && (!TARGET_ZERO_EXTEND_WITH_AND || optimize_function_for_size_p (cfun))"
+(define_insn "*zero_extendqihi2"
+ [(set (match_operand:HI 0 "register_operand" "=r")
+ (zero_extend:HI (match_operand:QI 1 "nonimmediate_operand" "qm")))]
+ "!(TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))"
"movz{bl|x}\t{%1, %k0|%k0, %1}"
[(set_attr "type" "imovx")
(set_attr "mode" "SI")])
-
-;; Rest is handled by single and.
-(define_split
- [(set (match_operand:SWI24 0 "register_operand" "")
- (zero_extend:SWI24 (match_operand:QI 1 "register_operand" "")))
- (clobber (reg:CC FLAGS_REG))]
- "reload_completed
- && true_regnum (operands[0]) == true_regnum (operands[1])"
- [(parallel [(set (match_dup 0) (and:SWI24 (match_dup 0) (const_int 255)))
- (clobber (reg:CC FLAGS_REG))])])
;; Sign extension instructions
@@ -7674,29 +7656,8 @@
switch (get_attr_type (insn))
{
case TYPE_IMOVX:
- {
- enum machine_mode mode;
+ return "#";
- gcc_assert (CONST_INT_P (operands[2]));
- if (INTVAL (operands[2]) == (HOST_WIDE_INT) 0xffffffff)
- mode = SImode;
- else if (INTVAL (operands[2]) == 0xffff)
- mode = HImode;
- else
- {
- gcc_assert (INTVAL (operands[2]) == 0xff);
- mode = QImode;
- }
-
- operands[1] = gen_lowpart (mode, operands[1]);
- if (mode == SImode)
- return "mov{l}\t{%1, %k0|%k0, %1}";
- else if (mode == HImode)
- return "movz{wl|x}\t{%1, %k0|%k0, %1}";
- else
- return "movz{bl|x}\t{%1, %k0|%k0, %1}";
- }
-
default:
gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (get_attr_mode (insn) == MODE_SI)
@@ -7717,7 +7678,7 @@
(set_attr "mode" "SI,DI,DI,SI")])
(define_insn "*andsi_1"
- [(set (match_operand:SI 0 "nonimmediate_operand" "=rm,r,r")
+ [(set (match_operand:SI 0 "nonimmediate_operand" "=rm,r,Ya")
(and:SI (match_operand:SI 1 "nonimmediate_operand" "%0,0,qm")
(match_operand:SI 2 "x86_64_general_operand" "re,rm,L")))
(clobber (reg:CC FLAGS_REG))]
@@ -7726,25 +7687,8 @@
switch (get_attr_type (insn))
{
case TYPE_IMOVX:
- {
- enum machine_mode mode;
+ return "#";
- gcc_assert (CONST_INT_P (operands[2]));
- if (INTVAL (operands[2]) == 0xffff)
- mode = HImode;
- else
- {
- gcc_assert (INTVAL (operands[2]) == 0xff);
- mode = QImode;
- }
-
- operands[1] = gen_lowpart (mode, operands[1]);
- if (mode == HImode)
- return "movz{wl|x}\t{%1, %0|%0, %1}";
- else
- return "movz{bl|x}\t{%1, %0|%0, %1}";
- }
-
default:
gcc_assert (rtx_equal_p (operands[0], operands[1]));
return "and{l}\t{%2, %0|%0, %2}";
@@ -7774,7 +7718,7 @@
(set_attr "mode" "SI")])
(define_insn "*andhi_1"
- [(set (match_operand:HI 0 "nonimmediate_operand" "=rm,r,r")
+ [(set (match_operand:HI 0 "nonimmediate_operand" "=rm,r,Ya")
(and:HI (match_operand:HI 1 "nonimmediate_operand" "%0,0,qm")
(match_operand:HI 2 "general_operand" "rn,rm,L")))
(clobber (reg:CC FLAGS_REG))]
@@ -7783,13 +7727,10 @@
switch (get_attr_type (insn))
{
case TYPE_IMOVX:
- gcc_assert (CONST_INT_P (operands[2]));
- gcc_assert (INTVAL (operands[2]) == 0xff);
- return "movz{bl|x}\t{%b1, %k0|%k0, %b1}";
+ return "#";
default:
gcc_assert (rtx_equal_p (operands[0], operands[1]));
-
return "and{w}\t{%2, %0|%0, %2}";
}
}
@@ -7829,6 +7770,44 @@
(set_attr "mode" "QI")])
(define_split
+ [(set (match_operand:SWI248 0 "register_operand" "")
+ (and:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "")
+ (match_operand:SWI248 2 "const_int_operand" "")))
+ (clobber (reg:CC FLAGS_REG))]
+ "reload_completed
+ && true_regnum (operands[0]) != true_regnum (operands[1])"
+ [(const_int 0)]
+{
+ enum machine_mode mode;
+
+ if (INTVAL (operands[2]) == (HOST_WIDE_INT) 0xffffffff)
+ mode = SImode;
+ else if (INTVAL (operands[2]) == 0xffff)
+ mode = HImode;
+ else
+ {
+ gcc_assert (INTVAL (operands[2]) == 0xff);
+ mode = QImode;
+ }
+
+ operands[1] = gen_lowpart (mode, operands[1]);
+
+ if (mode == SImode)
+ emit_insn (gen_zero_extendsidi2 (operands[0], operands[1]));
+ else
+ {
+ rtx (*insn) (rtx, rtx);
+
+ /* Zero extend to SImode to avoid partial register stalls. */
+ operands[0] = gen_lowpart (SImode, operands[0]);
+
+ insn = (mode == HImode) ? gen_zero_extendhisi2 : gen_zero_extendqisi2;
+ emit_insn (insn (operands[0], operands[1]));
+ }
+ DONE;
+})
+
+(define_split
[(set (match_operand 0 "register_operand" "")
(and (match_dup 0)
(const_int -65536)))
@@ -11175,18 +11154,17 @@
ix86_expand_clear (operands[3]);
})
-;; Similar, but match zero_extendhisi2_and, which adds a clobber.
+;; Similar, but match zero extend with andsi3.
(define_peephole2
[(set (reg FLAGS_REG) (match_operand 0 "" ""))
(set (match_operand:QI 1 "register_operand" "")
(match_operator:QI 2 "ix86_comparison_operator"
[(reg FLAGS_REG) (const_int 0)]))
- (parallel [(set (match_operand 3 "q_regs_operand" "")
- (zero_extend (match_dup 1)))
+ (parallel [(set (match_operand:SI 3 "q_regs_operand" "")
+ (and:SI (match_dup 3) (const_int 255)))
(clobber (reg:CC FLAGS_REG))])]
- "(peep2_reg_dead_p (3, operands[1])
- || operands_match_p (operands[1], operands[3]))
+ "REGNO (operands[1]) == REGNO (operands[3])
&& ! reg_overlap_mentioned_p (operands[3], operands[0])"
[(set (match_dup 4) (match_dup 0))
(set (strict_low_part (match_dup 5))
