RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 12:43:36 +01:00
Code Issues Projects Releases Wiki Activity
24,108 Commits 4 Branches 5 Tags 704 MiB
5c9d357d7c
Commit Graph

24108 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Chris Lattner
2bf9c8cc18 Plug in the byte and short splats 
llvm-svn: 27387
 2006-04-04 00:05:13 +00:00
Chris Lattner
0128e4d335 Revert accidentally committed hunks. 
llvm-svn: 27386
 2006-04-03 23:58:04 +00:00
Chris Lattner
57b9e01b3e Make sure to mark unsupported SCALAR_TO_VECTOR operations as expand. 
llvm-svn: 27385
 2006-04-03 23:55:43 +00:00
Evan Cheng
bbe72d932c Some SSE1 intrinsics: min, max, sqrt, etc. 
llvm-svn: 27384
 2006-04-03 23:49:17 +00:00
Chris Lattner
ab96554280 revert previous patch 
llvm-svn: 27383
 2006-04-03 23:14:49 +00:00
Evan Cheng
7ff32cd571 Use movlpd to: store lower f64 extracted from v2f64. 
Use movhpd to: store upper f64 extracted from v2f64.

llvm-svn: 27382
 2006-04-03 22:30:54 +00:00
Chris Lattner
eb9684f6a4 Force use of a frame-pointer if there is anything on the stack that is aligned 
more than the OS keeps the stack aligned.

llvm-svn: 27381
 2006-04-03 22:03:29 +00:00
Chris Lattner
4601b86ad0 The stack alignment is now computed dynamically, just verify it is correct. 
llvm-svn: 27380
 2006-04-03 21:39:57 +00:00
Chris Lattner
264e4a438a Remove unused method 
llvm-svn: 27379
 2006-04-03 21:39:03 +00:00
Chris Lattner
b46d7d9fc4 Keep track of max stack alignment as objects are added. Remove an obsolete method. 
llvm-svn: 27378
 2006-04-03 21:38:39 +00:00
Evan Cheng
169240beb7 - More efficient extract_vector_elt with shuffle and movss, movsd, movd, etc. 
- Some bug fixes and naming inconsistency fixes.

llvm-svn: 27377
 2006-04-03 20:53:28 +00:00
Chris Lattner
758878175b Align vectors to the size in bytes, not bits. 
llvm-svn: 27376
 2006-04-03 19:28:50 +00:00
Chris Lattner
d13dd8ef5c Add a missing check, this fixes UnitTests/Vector/sumarray.c 
llvm-svn: 27375
 2006-04-03 17:29:28 +00:00
Chris Lattner
d9902c3de0 Add a missing check, which broke a bunch of vector tests. 
llvm-svn: 27374
 2006-04-03 17:21:50 +00:00
Chris Lattner
29156e5094 shrinkify intrinsics more by using some local classes 
llvm-svn: 27373
 2006-04-03 17:20:06 +00:00
Chris Lattner
c65511b05c Add the full set of min/max instructions 
llvm-svn: 27372
 2006-04-03 15:58:28 +00:00
Chris Lattner
c0cba5e03f Add some classes to make it easier to define intrinsics. Add min/max intrinsics. 
llvm-svn: 27371
 2006-04-03 15:43:07 +00:00
Andrew Lenharth
4760eaae91 support x * (c1 + c2) where c1 and c2 are pow2s. special case for c2 == 4 
llvm-svn: 27370
 2006-04-03 04:19:17 +00:00
Andrew Lenharth
7d56275f4f test powers of 2 
llvm-svn: 27369
 2006-04-03 04:14:39 +00:00
Andrew Lenharth
af4a638eab mul by const conversion sequences. more coming soon 
llvm-svn: 27368
 2006-04-03 03:18:59 +00:00
Andrew Lenharth
b133e47444 back this out 
llvm-svn: 27367
 2006-04-03 03:16:50 +00:00
Andrew Lenharth
a6e52528c0 test some more mul by constant removal 
llvm-svn: 27366
 2006-04-03 03:16:09 +00:00
Andrew Lenharth
6aa31b3b67 Make sure mul by constant 5 is turned into a s4addq 
llvm-svn: 27365
 2006-04-02 21:47:07 +00:00
Andrew Lenharth
91c6f28ad6 This should be a win of every arch 
llvm-svn: 27364
 2006-04-02 21:42:45 +00:00
Andrew Lenharth
4c950de4c1 This makes McCat/12-IOtest go 8x faster or so 
llvm-svn: 27363
 2006-04-02 21:08:39 +00:00
Andrew Lenharth
067eaad4d9 This will be needed soon 
llvm-svn: 27362
 2006-04-02 20:13:57 +00:00
Reid Spencer
8cb87336b8 For PR722: 
Change the check for llvm-gcc from using LLVMGCCDIR to LLVMGCC. This checks
for the actual tool rather than the directory in which the tool resides. In
the case of this bug, it is possible that the directory exists but that the
tools in that directory do not. This fix should avoid the makefile from
erroneously proceeding without the actual tools being available.

llvm-svn: 27361
 2006-04-02 14:34:26 +00:00
Chris Lattner
fa82c33ae7 add a note 
llvm-svn: 27360
 2006-04-02 07:20:00 +00:00
Chris Lattner
8ba4723c74 Inform the dag combiner that the predicate compares only return a low bit. 
llvm-svn: 27359
 2006-04-02 06:26:07 +00:00
Chris Lattner
0b4f7786d2 relax assertion 
llvm-svn: 27358
 2006-04-02 06:19:46 +00:00
Chris Lattner
6433904644 Allow targets to compute masked bits for intrinsics. 
llvm-svn: 27357
 2006-04-02 06:15:09 +00:00
Chris Lattner
dbdc830c83 Add a little dag combine to compile this: 
int %AreSecondAndThirdElementsBothNegative(<4 x float>* %in) {
entry:
        %tmp1 = load <4 x float>* %in           ; <<4 x float>> [#uses=1]
        %tmp = tail call int %llvm.ppc.altivec.vcmpgefp.p( int 1, <4 x float> < float 0x7FF8000000000000, float 0.000000e+00, float 0.000000e+00, float 0x7FF8000000000000 >, <4 x float> %tmp1 )           ; <int> [#uses=1]
        %tmp = seteq int %tmp, 0                ; <bool> [#uses=1]
        %tmp3 = cast bool %tmp to int           ; <int> [#uses=1]
        ret int %tmp3
}

into this:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        lvx v0, 0, r3
        lvx v1, r5, r4
        vcmpgefp. v0, v1, v0
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        mtspr 256, r2
        blr

instead of this:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        lvx v0, 0, r3
        lvx v1, r5, r4
        vcmpgefp. v0, v1, v0
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        xori r3, r3, 1
        cntlzw r3, r3
        srwi r3, r3, 5
        mtspr 256, r2
        blr

llvm-svn: 27356
 2006-04-02 06:11:11 +00:00
Chris Lattner
42a1e621f1 vector casts of casts are eliminable. Transform this: 
%tmp = cast <4 x uint> %tmp to <4 x int>                ; <<4 x int>> [#uses=1]
        %tmp = cast <4 x int> %tmp to <4 x float>               ; <<4 x float>> [#uses=1]

into:

        %tmp = cast <4 x uint> %tmp to <4 x float>              ; <<4 x float>> [#uses=1]

llvm-svn: 27355
 2006-04-02 05:43:13 +00:00
Chris Lattner
d9ca6b5bfc vector casts never reinterpret bits 
llvm-svn: 27354
 2006-04-02 05:40:28 +00:00
Chris Lattner
3c994295fe Allow transforming this: 
%tmp = cast <4 x uint>* %testData to <4 x int>*         ; <<4 x int>*> [#uses=1]
        %tmp = load <4 x int>* %tmp             ; <<4 x int>> [#uses=1]

to this:

        %tmp = load <4 x uint>* %testData               ; <<4 x uint>> [#uses=1]
        %tmp = cast <4 x uint> %tmp to <4 x int>                ; <<4 x int>> [#uses=1]

llvm-svn: 27353
 2006-04-02 05:37:12 +00:00
Chris Lattner
cb26b2dfe8 Turn altivec lvx/stvx intrinsics into loads and stores. This allows the 
elimination of one load from this:

int AreSecondAndThirdElementsBothNegative( vector float *in ) {
#define QNaN 0x7FC00000
const vector unsigned int testData = (vector unsigned int)( QNaN, 0, 0, QNaN );
vector float test = vec_ld( 0, (float*) &testData );
return ! vec_any_ge( test, *in );
}

Now generating:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        addi r6, r1, -16
        lvx v0, r5, r4
        stvx v0, 0, r6
        lvx v1, 0, r3
        vcmpgefp. v0, v0, v1
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        xori r3, r3, 1
        cntlzw r3, r3
        srwi r3, r3, 5
        mtspr 256, r2
        blr

llvm-svn: 27352
 2006-04-02 05:30:25 +00:00
Chris Lattner
8967316b8c Remove done item 
llvm-svn: 27351
 2006-04-02 05:28:54 +00:00
Jeff Cohen
66d2c4d350 Fix tablegen related dependencies in Visual Studio. 
llvm-svn: 27350
 2006-04-02 05:20:53 +00:00
Chris Lattner
c76f9e8691 Implement promotion for EXTRACT_VECTOR_ELT, allowing v16i8 multiplies to work with PowerPC. 
llvm-svn: 27349
 2006-04-02 05:06:04 +00:00
Chris Lattner
9c24ec6de5 add a note 
llvm-svn: 27348
 2006-04-02 03:59:11 +00:00
Chris Lattner
f15063eadf Implement the Expand action for binary vector operations to break the binop 
into elements and operate on each piece.  This allows generic vector integer
multiplies to work on PPC, though the generated code is horrible.

llvm-svn: 27347
 2006-04-02 03:57:31 +00:00
Chris Lattner
389e309bfb Intrinsics that just load from memory can be treated like loads: they don't 
have to serialize against each other.  This allows us to schedule lvx's
across each other, for example.

llvm-svn: 27346
 2006-04-02 03:41:14 +00:00
Chris Lattner
9eacf6b01c Adjust the Intrinsics.gen interface a little bit 
llvm-svn: 27345
 2006-04-02 03:35:30 +00:00
Chris Lattner
e314cf19ba Adjust to change in Intrinsics.gen interface. 
llvm-svn: 27344
 2006-04-02 03:35:01 +00:00
Chris Lattner
104db817c8 Constant fold all of the vector binops. This allows us to compile this: 
"vector unsigned char mergeLowHigh = (vector unsigned char)
( 8, 9, 10, 11, 16, 17, 18, 19, 12, 13, 14, 15, 20, 21, 22, 23 );
vector unsigned char mergeHighLow = vec_xor( mergeLowHigh, vec_splat_u8(8));"

aka:

void %test2(<16 x sbyte>* %P) {
  store <16 x sbyte> cast (<4 x int> xor (<4 x int> cast (<16 x ubyte> < ubyte 8, ubyte 9, ubyte 10, ubyte 11, ubyte 16, ubyte 17, ubyte 18, ubyte 19, ubyte 12, ubyte 13, ubyte 14, ubyte 15, ubyte 20, ubyte 21, ubyte 22, ubyte 23 > to <4 x int>), <4 x int> cast (<16 x sbyte> < sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8 > to <4 x int>)) to <16 x sbyte>), <16 x sbyte> * %P
  ret void
}

into this:

_test2:
        mfspr r2, 256
        oris r4, r2, 32768
        mtspr 256, r4
        li r4, lo16(LCPI2_0)
        lis r5, ha16(LCPI2_0)
        lvx v0, r5, r4
        stvx v0, 0, r3
        mtspr 256, r2
        blr

instead of this:

_test2:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI2_0)
        lis r5, ha16(LCPI2_0)
        vspltisb v0, 8
        lvx v1, r5, r4
        vxor v0, v1, v0
        stvx v0, 0, r3
        mtspr 256, r2
        blr

... which occurs here:
http://developer.apple.com/hardware/ve/calcspeed.html

llvm-svn: 27343
 2006-04-02 03:25:57 +00:00
Chris Lattner
badebf1c9b Add a new -view-legalize-dags command line option 
llvm-svn: 27342
 2006-04-02 03:07:27 +00:00
Chris Lattner
52732a272f Implement constant folding of bit_convert of arbitrary constant vbuild_vector nodes. 
llvm-svn: 27341
 2006-04-02 02:53:43 +00:00
Chris Lattner
8a66373ad7 These entries already exist 
llvm-svn: 27340
 2006-04-02 02:51:27 +00:00
Chris Lattner
5eefd8e0b3 Add some missing node names 
llvm-svn: 27339
 2006-04-02 02:41:18 +00:00
Chris Lattner
99a3213376 simplify this method 
llvm-svn: 27338
 2006-04-02 02:28:52 +00:00