RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-26 14:33:02 +02:00
Code Issues Projects Releases Wiki Activity
24,866 Commits 4 Branches 5 Tags 704 MiB
a4b6f4749d
Commit Graph

217 Commits

Author SHA1 Message Date
Evan Cheng
a4b6f4749d No need to handle illegal types. 
llvm-svn: 28496
 2006-05-26 18:22:49 +00:00
Evan Cheng
f610c3e318 Consistency 
llvm-svn: 28488
 2006-05-25 23:31:23 +00:00
Evan Cheng
fb5e64ff9e Some clean up. 
llvm-svn: 28483
 2006-05-25 22:38:31 +00:00
Evan Cheng
ee280ac5d0 Remove some dead code. 
llvm-svn: 28481
 2006-05-25 22:25:52 +00:00
Evan Cheng
abb909e3bb Build breakage. 
llvm-svn: 28475
 2006-05-25 18:56:34 +00:00
Evan Cheng
bb17ad5ffa Switch X86 over to a call-selection model where the lowering code creates 
the copyto/fromregs instead of making the X86ISD::CALL selection code create
them.

llvm-svn: 28463
 2006-05-25 00:59:30 +00:00
Chris Lattner
ac9665d682 Fix file header comment 
llvm-svn: 28441
 2006-05-23 23:20:42 +00:00
Evan Cheng
3ef176507d Better way to check for vararg. 
llvm-svn: 28440
 2006-05-23 21:08:24 +00:00
Evan Cheng
65c3f3f26b Remove PreprocessCCCArguments and PreprocessFastCCArguments now that 
FORMAL_ARGUMENTS nodes include a token operand.

llvm-svn: 28439
 2006-05-23 21:06:34 +00:00
Chris Lattner
9aec97df10 Implement an annoying part of the Darwin/X86 abi: the callee of a struct 
return argument pops the hidden struct pointer if present, not the caller.

For example, in this testcase:

struct X { int D, E, F, G; };
struct X bar() {
  struct X a;
  a.D = 0;
  a.E = 1;
  a.F = 2;
  a.G = 3;
  return a;
}
void foo(struct X *P) {
  *P = bar();
}

We used to emit:

_foo:
        subl $28, %esp
        movl 32(%esp), %eax
        movl %eax, (%esp)
        call _bar
        addl $28, %esp
        ret
_bar:
        movl 4(%esp), %eax
        movl $0, (%eax)
        movl $1, 4(%eax)
        movl $2, 8(%eax)
        movl $3, 12(%eax)
        ret

This is correct on Linux/X86 but not Darwin/X86.  With this patch, we now
emit:

_foo:
        subl $28, %esp
        movl 32(%esp), %eax
        movl %eax, (%esp)
        call _bar
***     addl $24, %esp
        ret
_bar:
        movl 4(%esp), %eax
        movl $0, (%eax)
        movl $1, 4(%eax)
        movl $2, 8(%eax)
        movl $3, 12(%eax)
***     ret $4

For the record, GCC emits (which is functionally equivalent to our new code):

_bar:
        movl    4(%esp), %eax
        movl    $3, 12(%eax)
        movl    $2, 8(%eax)
        movl    $1, 4(%eax)
        movl    $0, (%eax)
        ret     $4
_foo:
        pushl   %esi
        subl    $40, %esp
        movl    48(%esp), %esi
        leal    16(%esp), %eax
        movl    %eax, (%esp)
        call    _bar
        subl    $4, %esp
        movl    16(%esp), %eax
        movl    %eax, (%esi)
        movl    20(%esp), %eax
        movl    %eax, 4(%esi)
        movl    24(%esp), %eax
        movl    %eax, 8(%esi)
        movl    28(%esp), %eax
        movl    %eax, 12(%esi)
        addl    $40, %esp
        popl    %esi
        ret

This fixes SingleSource/Benchmarks/CoyoteBench/fftbench with LLC and the
JIT, and fixes the X86-backend portion of PR729.  The CBE still needs to
be updated.

llvm-svn: 28438
 2006-05-23 18:50:38 +00:00
Chris Lattner
6d6a4d0e49 CSRet allows varargs 
llvm-svn: 28409
 2006-05-19 21:34:04 +00:00
Evan Cheng
d282cb8542 Should pass by reference. 
llvm-svn: 28357
 2006-05-17 19:07:40 +00:00
Chris Lattner
c04371da56 Implement the custom lowering hook right, returning values for all of the 
arguments at once.

llvm-svn: 28327
 2006-05-16 17:14:26 +00:00
Chris Lattner
f501a979ec Fix a bug I introduced yesterday, which broke functions with *no* arguments. 
llvm-svn: 28326
 2006-05-16 17:08:35 +00:00
Evan Cheng
dc9b5f5fc0 X86 integer register classes naming changes. Make them consistent with FP, vector classes. 
llvm-svn: 28324
 2006-05-16 07:21:53 +00:00
Chris Lattner
ba1dfc1da7 Add a chain to FORMAL_ARGUMENTS. This is a minimal port of the X86 backend, 
it doesn't currently use/maintain the chain properly.  Also, make the
X86ISelLowering.cpp file 80-col clean.

llvm-svn: 28320
 2006-05-16 06:45:34 +00:00
Chris Lattner
db8caed257 Dead variable 
llvm-svn: 28265
 2006-05-12 21:12:22 +00:00
Chris Lattner
89fa42b51e Teach the X86 backend about non-i32 inline asm register classes. 
llvm-svn: 28139
 2006-05-06 00:29:37 +00:00
Chris Lattner
a03676690b Teach the code generator to use cvtss2sd as extload f32 -> f64 
llvm-svn: 28131
 2006-05-05 21:35:18 +00:00
Owen Anderson
71bc529dfa Refactor TargetMachine, pushing handling of TargetData into the target-specific subclasses. This has one caller-visible change: getTargetData() now returns a pointer instead of a reference. 
This fixes PR 759.

llvm-svn: 28074
 2006-05-03 01:29:57 +00:00
Evan Cheng
a33feb51db Initial caller side support (for CCC only, not FastCC) of 128-bit vector 
passing by value.

llvm-svn: 28015
 2006-04-28 21:29:37 +00:00
Evan Cheng
d577ce4c4a Implement four-wide shuffle with 2 shufps if no more than two elements come 
from each vector. e.g.
        shuffle(G1, G2, 7, 1, 5, 2)
==>
        movaps _G2, %xmm0
        shufps $151, _G1, %xmm0
        shufps $216, %xmm0, %xmm0

llvm-svn: 28011
 2006-04-28 07:03:38 +00:00
Evan Cheng
f843942504 TargetLowering::LowerArguments should return a VBIT_CONVERT of 
FORMAL_ARGUMENTS SDOperand in the return result vector.

llvm-svn: 28009
 2006-04-28 05:25:15 +00:00
Evan Cheng
11e3cec8bd Make x86 isel lowering produce tailcall nodes. They are match to normal calls 
for now.

Patch contributed by Alexander Friedman.

llvm-svn: 27994
 2006-04-27 08:40:39 +00:00
Evan Cheng
24795120e1 Support for passing 128-bit vector arguments via XMM registers. 
llvm-svn: 27992
 2006-04-27 08:31:10 +00:00
Evan Cheng
1e065ae594 Oops 
llvm-svn: 27989
 2006-04-27 05:44:50 +00:00
Evan Cheng
a0e0eabc07 Bug fix: not updating NumIntRegs. 
llvm-svn: 27988
 2006-04-27 05:35:28 +00:00
Evan Cheng
a1f9f34f35 - Clean up formal argument lowering code. Prepare for vector pass by value work. 
- Fixed vararg support.

llvm-svn: 27985
 2006-04-27 01:32:22 +00:00
Evan Cheng
3abec16563 Fix fastcc failures. 
llvm-svn: 27980
 2006-04-26 18:21:31 +00:00
Evan Cheng
58d4133b60 Switching over FORMAL_ARGUMENTS mechanism to lower call arguments. 
llvm-svn: 27975
 2006-04-26 01:20:17 +00:00
Evan Cheng
09112df9d3 Separate LowerOperation() into multiple functions, one per opcode. 
llvm-svn: 27972
 2006-04-25 20:13:52 +00:00
Evan Cheng
0282b48ec2 Special case handling two wide build_vector(0, x). 
llvm-svn: 27961
 2006-04-24 22:58:52 +00:00
Evan Cheng
1eae7398a6 A little bit more build_vector enhancement for v8i16 cases. 
llvm-svn: 27959
 2006-04-24 18:01:45 +00:00
Evan Cheng
4812ce5035 MOVL shuffle (i.e. movd or movss / movsd from memory) of undef, V2 == V2 
llvm-svn: 27953
 2006-04-23 06:35:19 +00:00
Nate Begeman
7ed816f900 JumpTable support! What this represents is working asm and jit support for 
x86 and ppc for 100% dense switch statements when relocations are non-PIC.
This support will be extended and enhanced in the coming days to support
PIC, and less dense forms of jump tables.

llvm-svn: 27947
 2006-04-22 18:53:45 +00:00
Evan Cheng
1c33e83af5 Don't do all the lowering stuff for 2-wide build_vector's. Also, minor optimization for shuffle of undef. 
llvm-svn: 27946
 2006-04-22 08:34:05 +00:00
Evan Cheng
ec33bd04fb Fix a performance regression. Use {p}shuf* when there are only two distinct elements in a build_vector. 
llvm-svn: 27945
 2006-04-22 06:21:46 +00:00
Evan Cheng
5cb5fdd8eb Revamp build_vector lowering to take advantage of movss and movd instructions. 
movd always clear the top 96 bits and movss does so when it's loading the
value from memory.
The net result is codegen for 4-wide shuffles is much improved. It is near
optimal if one or more elements is a zero. e.g.

__m128i test(int a, int b) {
  return _mm_set_epi32(0, 0, b, a);
}

compiles to

_test:
	movd 8(%esp), %xmm1
	movd 4(%esp), %xmm0
	punpckldq %xmm1, %xmm0
	ret

compare to gcc:

_test:
	subl	$12, %esp
	movd	20(%esp), %xmm0
	movd	16(%esp), %xmm1
	punpckldq	%xmm0, %xmm1
	movq	%xmm1, %xmm0
	movhps	LC0, %xmm0
	addl	$12, %esp
	ret

or icc:

_test:
        movd      4(%esp), %xmm0                                #5.10
        movd      8(%esp), %xmm3                                #5.10
        xorl      %eax, %eax                                    #5.10
        movd      %eax, %xmm1                                   #5.10
        punpckldq %xmm1, %xmm0                                  #5.10
        movd      %eax, %xmm2                                   #5.10
        punpckldq %xmm2, %xmm3                                  #5.10
        punpckldq %xmm3, %xmm0                                  #5.10
        ret                                                     #5.10

There are still room for improvement, for example the FP variant of the above example:

__m128 test(float a, float b) {
  return _mm_set_ps(0.0, 0.0, b, a);
}

_test:
	movss 8(%esp), %xmm1
	movss 4(%esp), %xmm0
	unpcklps %xmm1, %xmm0
	xorps %xmm1, %xmm1
	movlhps %xmm1, %xmm0
	ret

The xorps and movlhps are unnecessary. This will require post legalizer optimization to handle.

llvm-svn: 27939
 2006-04-21 23:03:30 +00:00
Evan Cheng
e0289de5ab Now generating perfect (I think) code for "vector set" with a single non-zero 
scalar value.

e.g.
        _mm_set_epi32(0, a, 0, 0);
==>
	movd 4(%esp), %xmm0
	pshufd $69, %xmm0, %xmm0

        _mm_set_epi8(0, 0, 0, 0, 0, a, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
==>
	movzbw 4(%esp), %ax
	movzwl %ax, %eax
	pxor %xmm0, %xmm0
	pinsrw $5, %eax, %xmm0

llvm-svn: 27923
 2006-04-21 01:05:10 +00:00
Evan Cheng
41f2933444 - Added support to turn "vector clear elements", e.g. pand V, <-1, -1, 0, -1> 
to a vector shuffle.
- VECTOR_SHUFFLE lowering change in preparation for more efficient codegen
of vector shuffle with zero (or any splat) vector.

llvm-svn: 27875
 2006-04-20 08:58:49 +00:00
Evan Cheng
9dcd046bbd Handle v2i64 BUILD_VECTOR custom lowering correctly. v2i64 is a legal type, 
but i64 is not. If possible, change a i64 op to a f64 (e.g. load, constant)
and then cast it back.

llvm-svn: 27849
 2006-04-20 00:11:39 +00:00
Evan Cheng
d79f6a9f5a isSplatMask() bug: first element can be an undef. 
llvm-svn: 27847
 2006-04-19 23:28:59 +00:00
Evan Cheng
019dea6886 - Added support to do aribitrary 4 wide shuffle with no more than three 
instructions.
- Fixed a commute vector_shuff bug.

llvm-svn: 27845
 2006-04-19 22:48:17 +00:00
Evan Cheng
265831aa45 Commute vector_shuffle to match more movlhps, movlp{s|d} cases. 
llvm-svn: 27840
 2006-04-19 20:35:22 +00:00
Evan Cheng
98b1ca65dd Use movss to insert_vector_elt(v, s, 0). 
llvm-svn: 27782
 2006-04-17 22:45:49 +00:00
Evan Cheng
ecf13c5d79 Use two pinsrw to insert an element into v4i32 / v4f32 vector. 
llvm-svn: 27779
 2006-04-17 22:04:06 +00:00
Evan Cheng
4de1805c84 Implement v8i16, v16i8 splat using unpckl + pshufd. 
llvm-svn: 27768
 2006-04-17 20:43:08 +00:00
Chris Lattner
e1d38ad84b implement returns of a vector, testcase here: CodeGen/X86/vec_return.ll 
llvm-svn: 27767
 2006-04-17 20:32:50 +00:00
Evan Cheng
eb739d0355 FP SETOLT, SETOLT, SETUGE, SETUGT conditions were implemented incorrectly 
llvm-svn: 27755
 2006-04-17 07:24:10 +00:00
Evan Cheng
32e5d4f6bc Silly bug 
llvm-svn: 27719
 2006-04-15 05:37:34 +00:00