mirrors/llvm-project
0
0
Fork 0
mirror of https://github.com/llvm/llvm-project.git synced 2025-05-12 07:16:07 +00:00
Code Issues Projects Releases Wiki Activity
19,559 Commits 1,258 Branches 288 Tags
Commit Graph

1641 Commits

Author SHA1 Message Date
Chris Lattner
c9950c11a9 Add a new beta option for critical edge splitting, to avoid a problem that 
Nate noticed in yacr2 (and I know occurs in other places as well).

This is still rough, as the critical edge blocks are not intelligently placed
but is added to get some idea to see if this improves performance.

llvm-svn: 22825
 2005-08-17 06:37:43 +00:00
Chris Lattner
ba28c2733f Fix a regression on X86, where FP values can be promoted too. 
llvm-svn: 22822
 2005-08-17 06:06:25 +00:00
Jim Laskey
f2516a9180 Added generic code expansion for [signed|unsigned] i32 to [f32|f64] casts in the 
legalizer.  PowerPC now uses this expansion instead of ISel version.

Example:

// signed integer to double conversion
double f1(signed x) {
  return (double)x;
}

// unsigned integer to double conversion
double f2(unsigned x) {
  return (double)x;
}

// signed integer to float conversion
float f3(signed x) {
  return (float)x;
}

// unsigned integer to float conversion
float f4(unsigned x) {
  return (float)x;
}


Byte Code:

internal fastcc double %_Z2f1i(int %x) {
entry:
        %tmp.1 = cast int %x to double          ; <double> [#uses=1]
        ret double %tmp.1
}

internal fastcc double %_Z2f2j(uint %x) {
entry:
        %tmp.1 = cast uint %x to double         ; <double> [#uses=1]
        ret double %tmp.1
}

internal fastcc float %_Z2f3i(int %x) {
entry:
        %tmp.1 = cast int %x to float           ; <float> [#uses=1]
        ret float %tmp.1
}

internal fastcc float %_Z2f4j(uint %x) {
entry:
        %tmp.1 = cast uint %x to float          ; <float> [#uses=1]
        ret float %tmp.1
}

internal fastcc double %_Z2g1i(int %x) {
entry:
        %buffer = alloca [2 x uint]             ; <[2 x uint]*> [#uses=3]
        %tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0                ; <uint*> [#uses=1]
        store uint 1127219200, uint* %tmp.0
        %tmp.2 = cast int %x to uint            ; <uint> [#uses=1]
        %tmp.3 = xor uint %tmp.2, 2147483648            ; <uint> [#uses=1]
        %tmp.5 = getelementptr [2 x uint]* %buffer, int 0, int 1                ; <uint*> [#uses=1]
        store uint %tmp.3, uint* %tmp.5
        %tmp.9 = cast [2 x uint]* %buffer to double*            ; <double*> [#uses=1]
        %tmp.10 = load double* %tmp.9           ; <double> [#uses=1]
        %tmp.13 = load double* cast (long* %signed_bias to double*)             ; <double> [#uses=1]
        %tmp.14 = sub double %tmp.10, %tmp.13           ; <double> [#uses=1]
        ret double %tmp.14
}

internal fastcc double %_Z2g2j(uint %x) {
entry:
        %buffer = alloca [2 x uint]             ; <[2 x uint]*> [#uses=3]
        %tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0                ; <uint*> [#uses=1]
        store uint 1127219200, uint* %tmp.0
        %tmp.1 = getelementptr [2 x uint]* %buffer, int 0, int 1                ; <uint*> [#uses=1]
        store uint %x, uint* %tmp.1
        %tmp.4 = cast [2 x uint]* %buffer to double*            ; <double*> [#uses=1]
        %tmp.5 = load double* %tmp.4            ; <double> [#uses=1]
        %tmp.8 = load double* cast (long* %unsigned_bias to double*)            ; <double> [#uses=1]
        %tmp.9 = sub double %tmp.5, %tmp.8              ; <double> [#uses=1]
        ret double %tmp.9
}

internal fastcc float %_Z2g3i(int %x) {
entry:
        %buffer = alloca [2 x uint]             ; <[2 x uint]*> [#uses=3]
        %tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0                ; <uint*> [#uses=1]
        store uint 1127219200, uint* %tmp.0
        %tmp.2 = cast int %x to uint            ; <uint> [#uses=1]
        %tmp.3 = xor uint %tmp.2, 2147483648            ; <uint> [#uses=1]
        %tmp.5 = getelementptr [2 x uint]* %buffer, int 0, int 1                ; <uint*> [#uses=1]
        store uint %tmp.3, uint* %tmp.5
        %tmp.9 = cast [2 x uint]* %buffer to double*            ; <double*> [#uses=1]
        %tmp.10 = load double* %tmp.9           ; <double> [#uses=1]
        %tmp.13 = load double* cast (long* %signed_bias to double*)             ; <double> [#uses=1]
        %tmp.14 = sub double %tmp.10, %tmp.13           ; <double> [#uses=1]
        %tmp.16 = cast double %tmp.14 to float          ; <float> [#uses=1]
        ret float %tmp.16
}

internal fastcc float %_Z2g4j(uint %x) {
entry:
        %buffer = alloca [2 x uint]             ; <[2 x uint]*> [#uses=3]
        %tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0                ; <uint*> [#uses=1]
        store uint 1127219200, uint* %tmp.0
        %tmp.1 = getelementptr [2 x uint]* %buffer, int 0, int 1                ; <uint*> [#uses=1]
        store uint %x, uint* %tmp.1
        %tmp.4 = cast [2 x uint]* %buffer to double*            ; <double*> [#uses=1]
        %tmp.5 = load double* %tmp.4            ; <double> [#uses=1]
        %tmp.8 = load double* cast (long* %unsigned_bias to double*)            ; <double> [#uses=1]
        %tmp.9 = sub double %tmp.5, %tmp.8              ; <double> [#uses=1]
        %tmp.11 = cast double %tmp.9 to float           ; <float> [#uses=1]
        ret float %tmp.11
}


PowerPC Code:

        .machine ppc970


        .const
        .align  2
.CPIl1__Z2f1i_0:                                        ; float 0x4330000080000000
        .long   1501560836      ; float 4.5036e+15
        .text
        .align  2
        .globl  l1__Z2f1i
l1__Z2f1i:
.LBBl1__Z2f1i_0:        ; entry
        xoris r2, r3, 32768
        stw r2, -4(r1)
        lis r2, 17200
        stw r2, -8(r1)
        lfd f0, -8(r1)
        lis r2, ha16(.CPIl1__Z2f1i_0)
        lfs f1, lo16(.CPIl1__Z2f1i_0)(r2)
        fsub f1, f0, f1
        blr


        .const
        .align  2
.CPIl2__Z2f2j_0:                                        ; float 0x4330000000000000
        .long   1501560832      ; float 4.5036e+15
        .text
        .align  2
        .globl  l2__Z2f2j
l2__Z2f2j:
.LBBl2__Z2f2j_0:        ; entry
        stw r3, -4(r1)
        lis r2, 17200
        stw r2, -8(r1)
        lfd f0, -8(r1)
        lis r2, ha16(.CPIl2__Z2f2j_0)
        lfs f1, lo16(.CPIl2__Z2f2j_0)(r2)
        fsub f1, f0, f1
        blr


        .const
        .align  2
.CPIl3__Z2f3i_0:                                        ; float 0x4330000080000000
        .long   1501560836      ; float 4.5036e+15
        .text
        .align  2
        .globl  l3__Z2f3i
l3__Z2f3i:
.LBBl3__Z2f3i_0:        ; entry
        xoris r2, r3, 32768
        stw r2, -4(r1)
        lis r2, 17200
        stw r2, -8(r1)
        lfd f0, -8(r1)
        lis r2, ha16(.CPIl3__Z2f3i_0)
        lfs f1, lo16(.CPIl3__Z2f3i_0)(r2)
        fsub f0, f0, f1
        frsp f1, f0
        blr


        .const
        .align  2
.CPIl4__Z2f4j_0:                                        ; float 0x4330000000000000
        .long   1501560832      ; float 4.5036e+15
        .text
        .align  2
        .globl  l4__Z2f4j
l4__Z2f4j:
.LBBl4__Z2f4j_0:        ; entry
        stw r3, -4(r1)
        lis r2, 17200
        stw r2, -8(r1)
        lfd f0, -8(r1)
        lis r2, ha16(.CPIl4__Z2f4j_0)
        lfs f1, lo16(.CPIl4__Z2f4j_0)(r2)
        fsub f0, f0, f1
        frsp f1, f0
        blr

llvm-svn: 22814
 2005-08-17 00:39:29 +00:00
Chris Lattner
0d2456e1f0 add a new TargetConstant node 
llvm-svn: 22813
 2005-08-17 00:34:06 +00:00
Chris Lattner
33182325f5 Eliminate the RegSDNode class, which 3 nodes (CopyFromReg/CopyToReg/ImplicitDef) 
used to tack a register number onto the node.

Instead of doing this, make a new node, RegisterSDNode, which is a leaf
containing a register number.  These three operations just become normal
DAG nodes now, instead of requiring special handling.

Note that with this change, it is no longer correct to make illegal
CopyFromReg/CopyToReg nodes.  The legalizer will not touch them, and this
is bad, so don't do it. :)

llvm-svn: 22806
 2005-08-16 21:55:35 +00:00
Nate Begeman
371e49515d Implement BR_CC and BRTWOWAY_CC. This allows the removal of a rather nasty 
fixme from the PowerPC backend.  Emit slightly better code for legalizing
select_cc.

llvm-svn: 22805
 2005-08-16 19:49:35 +00:00
Chris Lattner
bc89226527 Allow passing a dag into dump and getOperationName. If one is available 
when printing a node, use it to render target operations with their
target instruction name instead of "<<unknown>>".

llvm-svn: 22804
 2005-08-16 18:33:07 +00:00
Chris Lattner
7e57d18b79 Use a extant helper to do this. 
llvm-svn: 22802
 2005-08-16 18:31:23 +00:00
Chris Lattner
1973278b38 Add some methods for dag->dag isel. 
Split RemoveNodeFromCSEMaps out of DeleteNodesIfDead to do it.

llvm-svn: 22801
 2005-08-16 18:17:10 +00:00
Nate Begeman
d5e739dcc2 Fix last night's PPC32 regressions by 
1. Not selecting the false value of a select_cc in the false arm, which
   isn't legal for nested selects.
2. Actually returning the node we created and Legalized in the FP_TO_UINT
   Expander.

llvm-svn: 22789
 2005-08-14 18:38:32 +00:00
Nate Begeman
36853ee1fd Teach the legalizer how to legalize FP_TO_UINT. 
Teach the legalizer to promote FP_TO_UINT to FP_TO_SINT if the wider
  FP_TO_UINT is also illegal.  This allows us on PPC to codegen
  unsigned short foo(float a) { return a; }

as:
_foo:
.LBB_foo_0:     ; entry
        fctiwz f0, f1
        stfd f0, -8(r1)
        lwz r2, -4(r1)
        rlwinm r3, r2, 0, 16, 31
        blr

instead of:
_foo:
.LBB_foo_0:     ; entry
        fctiwz f0, f1
        stfd f0, -8(r1)
        lwz r2, -4(r1)
        lis r3, ha16(.CPI_foo_0)
        lfs f0, lo16(.CPI_foo_0)(r3)
        fcmpu cr0, f1, f0
        blt .LBB_foo_2  ; entry
.LBB_foo_1:     ; entry
        fsubs f0, f1, f0
        fctiwz f0, f0
        stfd f0, -16(r1)
        lwz r2, -12(r1)
        xoris r2, r2, 32768
.LBB_foo_2:     ; entry
        rlwinm r3, r2, 0, 16, 31
        blr

llvm-svn: 22785
 2005-08-14 01:20:53 +00:00
Nate Begeman
dc3154ec66 Remove an unncessary argument to SimplifySelectCC and add an additional 
assert when creating a select_cc node.

llvm-svn: 22780
 2005-08-13 06:14:17 +00:00
Nate Begeman
b6651e81a0 Fix the fabs regression on x86 by abstracting the select_cc optimization 
out into SimplifySelectCC.  This allows both ISD::SELECT and ISD::SELECT_CC
to use the same set of simplifying folds.

llvm-svn: 22779
 2005-08-13 06:00:21 +00:00
Chris Lattner
21381e8424 implement a couple of simple shift foldings. 
e.g.  (X & 7) >> 3   -> 0

llvm-svn: 22774
 2005-08-12 23:54:58 +00:00
Nate Begeman
5c7656fd53 Add a select_cc optimization for recognizing abs(int). This speeds up an 
integer MPEG encoding loop by a factor of two.

llvm-svn: 22758
 2005-08-11 02:18:13 +00:00
Nate Begeman
180b08897f Some SELECT_CC cleanups: 
1. move assertions for node creation to getNode()
2. legalize the values returned in ExpandOp immediately
3. Move select_cc optimizations from SELECT's getNode() to SELECT_CC's,
   allowing them to be cleaned up significantly.

This paves the way to pick up additional optimizations on SELECT_CC, such
as sum-of-absolute-differences.

llvm-svn: 22757
 2005-08-11 01:12:20 +00:00
Nate Begeman
e5b86d7442 Add new node, SELECT_CC. This node is for targets that don't natively 
implement SELECT.

llvm-svn: 22755
 2005-08-10 20:51:12 +00:00
Chris Lattner
21c0fd9e8f Fix an oversight that may be causing PR617. 
llvm-svn: 22753
 2005-08-10 17:37:53 +00:00
Chris Lattner
679f5b0b40 Fix spelling, fix some broken canonicalizations by my last patch 
llvm-svn: 22734
 2005-08-09 23:09:05 +00:00
Chris Lattner
14e060f743 add cc nodes to the AllNodes list so they show up in Graphviz output 
llvm-svn: 22731
 2005-08-09 20:40:02 +00:00
Chris Lattner
d47675ed24 Eliminate the SetCCSDNode in favor of a CondCodeSDNode class. This pulls the 
CC out of the SetCC operation, making SETCC a standard ternary operation and
CC's a standard DAG leaf.  This will make it possible for other node to use
CC's as operands in the future...

llvm-svn: 22728
 2005-08-09 20:20:18 +00:00
Chris Lattner
88e2d2ee6b Handle 64-bit constant exprs on 64-bit targets. 
llvm-svn: 22696
 2005-08-08 04:26:32 +00:00
Chris Lattner
0c26a0b902 add a small simplification that can be exposed after promotion/expansion 
llvm-svn: 22691
 2005-08-07 05:00:44 +00:00
Chris Lattner
96ad31321a Change FindEarliestCallSeqEnd (used by libcall insertion) to use a set to 
avoid revisiting nodes more than once.  This eliminates a source of
potentially exponential behavior.  For a small function in 191.fma3d
(hexah_stress_divergence_), this speeds up isel from taking > 20mins to
taking 0.07s.

llvm-svn: 22680
 2005-08-05 18:10:27 +00:00
Chris Lattner
1095dc94a9 Fix a use-of-dangling-pointer bug, from the introduction of SrcValue's. 
llvm-svn: 22679
 2005-08-05 16:55:31 +00:00
Chris Lattner
cabdc34563 Fix a latent bug in the libcall inserter that was exposed by Nate's patch 
yesterday.  This fixes whetstone and a bunch of programs in the External tests.

llvm-svn: 22678
 2005-08-05 16:23:57 +00:00
Nate Begeman
77558da546 Fix a fixme in LegalizeDAG 
llvm-svn: 22661
 2005-08-04 21:43:28 +00:00
Misha Brukman
a54e201edf * Unbreak release build 
* Add comments to #endif pragmas for readability

llvm-svn: 22647
 2005-08-04 14:22:41 +00:00
Chris Lattner
8191442548 Fix PR611, codegen'ing SREM of FP operands to fmod or fmodf instead of 
the sequence used for integer ops

llvm-svn: 22629
 2005-08-03 20:31:37 +00:00
Chris Lattner
6667bdbaca Update to use the new MathExtras.h support for log2 computation. 
Patch contributed by Jim Laskey!

llvm-svn: 22594
 2005-08-02 19:26:06 +00:00
Chris Lattner
4398daf069 Fix casts from long to sbyte on ppc 
llvm-svn: 22570
 2005-08-01 18:16:37 +00:00
Jeff Cohen
546fd5944e Keep tabs and trailing spaces out. 
llvm-svn: 22565
 2005-07-30 18:33:25 +00:00
Chris Lattner
941d84a34d fix float->long conversions on x86 
llvm-svn: 22563
 2005-07-30 01:40:57 +00:00
Chris Lattner
f59b2daddb Allow targets to have custom expanders for FP_TO_*INT conversions where 
both the src and dest values are legal

llvm-svn: 22555
 2005-07-30 00:04:12 +00:00
Chris Lattner
fe68d75aad Allow targets to define custom expanders for FP_TO_*INT 
llvm-svn: 22548
 2005-07-29 00:33:32 +00:00
Chris Lattner
44fe26ff07 allow a target to request that unknown FP_TO_*INT conversion be promoted to 
a larger integer destination.

llvm-svn: 22547
 2005-07-29 00:11:56 +00:00
Chris Lattner
f99f8f9081 instead of having all conversions be handled by one case value, and then have 
subcases inside, break things out earlier.

llvm-svn: 22546
 2005-07-28 23:31:12 +00:00
Andrew Lenharth
3faa82219a new is not a valid default anywhere, so make this pure virtual 
llvm-svn: 22542
 2005-07-28 18:13:59 +00:00
Chris Lattner
96cbfbbeaf Fix debug info to not print out recently freed memory. 
llvm-svn: 22529
 2005-07-27 23:11:25 +00:00
Chris Lattner
9937713252 Print symbolic register names in debug dumps 
llvm-svn: 22528
 2005-07-27 23:03:38 +00:00
Jeff Cohen
5f4ef3c5a8 Eliminate all remaining tabs and trailing spaces. 
llvm-svn: 22523
 2005-07-27 06:12:32 +00:00
Nate Begeman
1ac40a1245 Remove unnecessary FP_EXTEND. This causes worse codegen for SSE. 
llvm-svn: 22469
 2005-07-19 16:50:03 +00:00
Chris Lattner
b35912e421 The assertion was wrong: the code only worked for i64. While we're at it, 
expand the code to work for all integer datatypes.  This should unbreak
alpha.

llvm-svn: 22464
 2005-07-18 04:31:14 +00:00
Chris Lattner
a5998ce94f Only get the .bss and .data sections when needed instead of unconditionally. 
This allows is to not emit empty sections when .data or .bss is not used.

llvm-svn: 22457
 2005-07-16 17:41:06 +00:00
Chris Lattner
363964e53d Refactor getSection() method to make it easier to use. 
llvm-svn: 22455
 2005-07-16 17:36:04 +00:00
Chris Lattner
fd44500427 Major refactor of the ELFWriter code. Instead of building up one big 
vector that represents the .o file at once, build up a vector for each
section of the .o file.  This is needed because the .o file writer needs
to be able to switch between sections as it emits them (e.g. switch
between the .text section and the .rel section when emitting code).

This patch has no functionality change.

llvm-svn: 22453
 2005-07-16 08:01:13 +00:00
Nate Begeman
7e74c834c1 Teach the legalizer how to promote SINT_TO_FP to a wider SINT_TO_FP that 
the target natively supports.  This eliminates some special-case code from
the x86 backend and generates better code as well.

For an i8 to f64 conversion, before & after:

_x87 before:
        subl $2, %esp
        movb 6(%esp), %al
        movsbw %al, %ax
        movw %ax, (%esp)
        filds (%esp)
        addl $2, %esp
        ret

_x87 after:
        subl $2, %esp
        movsbw 6(%esp), %ax
        movw %ax, (%esp)
        filds (%esp)
        addl $2, %esp
        ret

_sse before:
        subl $12, %esp
        movb 16(%esp), %al
        movsbl %al, %eax
        cvtsi2sd %eax, %xmm0
        addl $12, %esp
        ret

_sse after:
        subl $12, %esp
        movsbl 16(%esp), %eax
        cvtsi2sd %eax, %xmm0
        addl $12, %esp
        ret

llvm-svn: 22452
 2005-07-16 02:02:34 +00:00
Chris Lattner
e3e847bfd7 Break the code for expanding UINT_TO_FP operations out into its own 
SelectionDAGLegalize::ExpandLegalUINT_TO_FP method.

Add a new method, PromoteLegalUINT_TO_FP, which allows targets to request
that UINT_TO_FP operations be promoted to a larger input type.  This is
useful for targets that have some UINT_TO_FP or SINT_TO_FP operations but
not all of them (like X86).

The same should be done with SINT_TO_FP, but this patch does not do that
yet.

llvm-svn: 22447
 2005-07-16 00:19:57 +00:00
Chris Lattner
b47f5e6d54 You can't use config options without config.h 
llvm-svn: 22446
 2005-07-15 22:48:31 +00:00
Chris Lattner
46524e2573 Make this use the new autoconf support for finding the executables for 
gv and Graphviz.

llvm-svn: 22434
 2005-07-14 05:33:13 +00:00