Commit Graph

2644 Commits

Author SHA1 Message Date
Eli Friedman
b4b8b0cc90 Add a target-specific branchless method for double-width relational
comparisons on x86.  Essentially, the way this works is that SUB+SBB sets
the relevant flags the same way a double-width CMP would.

This is a substantial improvement over the generic lowering in LLVM. The output
is also shorter than the gcc-generated output; I haven't done any detailed
benchmarking, though.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127852 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-18 02:34:11 +00:00
Benjamin Kramer
1c10b8de46 BuildUDIV: If the divisor is even we can simplify the fixup of the multiplied value by introducing an early shift.
This allows us to compile "unsigned foo(unsigned x) { return x/28; }" into
	shrl	$2, %edi
	imulq	$613566757, %rdi, %rax
	shrq	$32, %rax
	ret

instead of
	movl    %edi, %eax
	imulq   $613566757, %rax, %rcx
	shrq    $32, %rcx
	subl    %ecx, %eax
	shrl    %eax
	addl    %ecx, %eax
	shrl    $4, %eax

on x86_64

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127829 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-17 20:39:14 +00:00
NAKAMURA Takumi
1aa7f7a997 test/CodeGen/X86/h-registers-1.ll: Add explicit -mtriple=x86_64-linux. It does not need to be checked on x86_64-win32 (aka Win64).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127800 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-17 04:24:40 +00:00
NAKAMURA Takumi
ede4e28ca3 test/CodeGen/X86/constant-pool-remat-0.ll: FileCheck-ize and add explicit -mtriple=x86_64-linux.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127775 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 23:01:31 +00:00
Cameron Zwarich
ebe8173941 The x86-64 ABI says that a bool is only guaranteed to be sign-extended to a byte
rather than an int. Thankfully, this only causes LLVM to miss optimizations, not
generate incorrect code.

This just fixes the zext at the return. We still insert an i32 ZextAssert when
reading a function's arguments, but it is followed by a truncate and another i8
ZextAssert so it is not optimized.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127766 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 22:20:18 +00:00
Cameron Zwarich
7be4b7ed75 Rename a test to be more inclusive.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127765 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 22:20:12 +00:00
Cameron Zwarich
0a00615b34 Add a test for i1 zeroext arguments on x86-64. We currently generate code that
conforms to the ABI, but DAGCombine could in theory recognize the sequence of
zext asserts and truncates and generate incorrect code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127754 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 20:15:44 +00:00
NAKAMURA Takumi
bfc4c983a6 test/CodeGen/X86: FileCheck-ize and add actions for x86_64-linux and x86_64-win32.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127734 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 13:53:07 +00:00
NAKAMURA Takumi
37947c6bad test/CodeGen/X86: Add a pattern for Win64.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127733 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 13:52:51 +00:00
NAKAMURA Takumi
ddbfbcf72e test/CodeGen/X86: FileCheck-ize and add explicit -mtriple=x86_64-linux. They are useless to Win64 target.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127732 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 13:52:38 +00:00
NAKAMURA Takumi
4491aa49b3 test/CodeGen/X86/byval*.ll: Win64 has not supported byval yet.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127731 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 13:52:20 +00:00
NAKAMURA Takumi
67bf77e8fd test/CodeGen/X86/dyn-stackalloc.ll: FileCheck-ize.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127730 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-16 13:52:08 +00:00
Evan Cheng
bf34a5ec22 sext(undef) = 0, because the top bits will all be the same.
zext(undef) = 0, because the top bits will be zero.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127649 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-15 02:22:10 +00:00
Cameron Zwarich
899eaa3569 Roll r127459 back in:
Optimize trivial branches in CodeGenPrepare, which often get created from the
lowering of objectsize intrinsics. Unfortunately, a number of tests were relying
on llc not optimizing trivial branches, so I had to add an option to allow them
to continue to test what they originally tested.

This fixes <rdar://problem/8785296> and <rdar://problem/9112893>.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127498 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-11 21:52:04 +00:00
Cameron Zwarich
53aac15a60 Fix the GCC test suite issue exposed by r127477, which was caused by stack
protector insertion not working correctly with unreachable code. Since that
revision was rolled out, this test doesn't actual fail before this fix.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127497 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-11 21:51:56 +00:00
Daniel Dunbar
950d3db5f4 Revert r127459, "Optimize trivial branches in CodeGenPrepare, which often get
created from the", it broke some GCC test suite tests.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127477 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-11 19:30:30 +00:00
Cameron Zwarich
592ca3fda9 Optimize trivial branches in CodeGenPrepare, which often get created from the
lowering of objectsize intrinsics. Unfortunately, a number of tests were relying
on llc not optimizing trivial branches, so I had to add an option to allow them
to continue to test what they originally tested.

This fixes <rdar://problem/8785296> and <rdar://problem/9112893>.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127459 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-11 04:54:27 +00:00
Eric Christopher
de5e101b0d Change the x86 32-bit scheduler to register pressure and fix up the
corresponding testcases back to the previous versions.

Fixes some performance regressions only seen on 32-bit.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127441 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-11 01:05:58 +00:00
Stuart Hastings
03d5826164 Revert 127359; it broke lencod.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127382 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-10 00:25:53 +00:00
Benjamin Kramer
7bff3e7c1b Fix mistyped CHECK lines.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127366 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 22:07:31 +00:00
Stuart Hastings
167831dcac Tweak test to work on Linux.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127364 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 21:35:10 +00:00
Stuart Hastings
2f5443be11 Disable this test temporarily to reduce BuildBot complaints.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127363 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 21:33:47 +00:00
Stuart Hastings
2f26fa4838 X86 byval copies no longer always_inline. <rdar://problem/8706628>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127359 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 21:10:30 +00:00
Jakob Stoklund Olesen
5d96e5a1cc Make physreg coalescing independent on the number of uses of the virtual register.
The damage done by physreg coalescing only depends on the number of instructions
the extended physreg live range covers. This fixes PR9438.

The heuristic is still luck-based, and physreg coalescing really should be
disabled completely. We need a register allocator with better hinting support
before that is possible.

Convert a test to FileCheck and force spilling by inserting an extra call. The
previous spilling behavior was dependent on misguided physreg coalescing
decisions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127351 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 19:27:06 +00:00
Jakob Stoklund Olesen
dda386c44d Delete a test case that is very sensitive to coalescer behavior.
The test is derived from an old miscompilation of
MultiSource/Benchmarks/VersaBench/8b10b which is run regularly, so we are not
losing coverage.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127350 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 19:27:02 +00:00
Andrew Trick
5d332e0c3e This test case should work with list-ilp or list-burr.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127348 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 19:17:10 +00:00
NAKAMURA Takumi
3ca99435e9 Target/X86: Tweak va_arg for Win64 not to miss taking va_start when number of fixed args > 4.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127328 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 11:33:15 +00:00
Eric Christopher
e11128dd9d Fix testcase.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127298 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-09 00:41:41 +00:00
Benjamin Kramer
e5ef311ee3 Strip cruft.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127269 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-08 20:19:10 +00:00
Eric Christopher
2b24e7f3df Add a testcase for r127263.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127266 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-08 19:49:15 +00:00
Benjamin Kramer
c175a4bd7e X86: Fix the (saddo/ssub x, 1) -> incl/decl selection to check the right operand for 1.
Found by inspection.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127247 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-08 15:20:20 +00:00
Eric Christopher
7c2cdb1c05 Turn on list-ilp scheduling by default on x86 and x86-64, fix up
testcases accordingly. Some are currently xfailed and will be filed
as bugs to be fixed or understood.

Performance results:

roughly neutral on SPEC
some micro benchmarks in the llvm suite are up between 100 and 150%, only
a pair of regressions that are due to be investigated

john-the-ripper saw:
10% improvement in traditional DES
8% improvement in BSDI DES
59% improvement in FreeBSD MD5
67% improvement in OpenBSD Blowfish
14% improvement in LM DES

Small compile time impact.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127208 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-08 02:42:25 +00:00
NAKAMURA Takumi
89be0acecf test/CodeGen/X86/vec_cast.ll: [PR8311] Add explicit -mtriple=x86_64-linux and -mtriple=x86_64-win32. Thanks to Nadav, it might be fixed in r126424.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127060 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-05 02:38:02 +00:00
Dan Gohman
a7a841adb8 When decling to reuse existing expressions that involve casts, ignore
bitcasts, which are really no-ops here. This fixes slowdowns on
MultiSource/Applications/aha and others.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127031 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-04 20:46:46 +00:00
Joerg Sonnenberger
89e0f386f3 Be nice to Xcore and the XMOS assembler and avoid quoting section names
that contain only letters, digits and the characters "_" and ".".


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127028 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-04 20:03:14 +00:00
Eli Friedman
81c5ef8649 Revert r123908; the code in question is completely untested and wrong.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126964 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-03 22:33:23 +00:00
Joerg Sonnenberger
ea83b13350 Bug#9033: For the ELF assembler output, always quote the section name.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126963 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-03 22:31:08 +00:00
Stuart Hastings
44456e86c8 Test case for r126864. Radar 9056407.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126900 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-02 23:41:40 +00:00
David Greene
a20244d1ba [AVX] Fix mask predicates for 256-bit UNPCKLPS/D and implement
missing patterns for them.

      Add a SIMD test subdirectory to hold tests for SIMD instruction
      selection correctness and quality.
'


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126845 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-02 17:23:43 +00:00
Cameron Zwarich
56e3793acf Eliminate the unused CodeGenPrepare option to split critical edges.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126825 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-02 03:31:46 +00:00
Dan Gohman
0cbe91ba3b Don't re-use existing addrec expansions if they contain casts.
This fixes PR9259.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126812 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-02 01:34:10 +00:00
Evan Cheng
f06e6c2ba7 Catch more cases where 2-address pass should 3-addressify instructions. rdar://9002648.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126811 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-02 01:08:17 +00:00
Duncan Sands
377ffe3b11 Windows codegen also dies on this, so restrict to the platform it was
actually tested on.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126652 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-28 14:22:08 +00:00
Duncan Sands
443612e165 Make this test x86 specific because the ARM backend can't handle it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126650 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-28 12:30:47 +00:00
NAKAMURA Takumi
419f232783 Target/X86: Always emit "push/pop GPRs" in prologue/epilogue and emit "spill/reload frames" for XMMs.
It improves Win64's prologue/epilogue but it would not affect ia32 and amd64 (lack of nonvolatile XMMs).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126568 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-27 08:47:19 +00:00
Cameron Zwarich
eee444cc4e Fix PR9324 / <rdar://problem/9052489> by handling the case where a PHI has no uses.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126567 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-27 08:06:01 +00:00
Cameron Zwarich
60c8b22dad Give a test file a more sensible name so that it can hold more test cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126566 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-27 08:05:57 +00:00
Benjamin Kramer
7466678003 Add some DAGCombines for (adde 0, 0, glue), which are useful to optimize legalized code for large integer arithmetic.
1. Inform users of ADDEs with two 0 operands that it never sets carry
2. Fold other ADDs or ADDCs into the ADDE if possible

It would be neat if we could do the same thing for SETCC+ADD eventually, but we can't do that in target independent code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126557 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-26 22:48:07 +00:00
Nadav Rotem
8c20ec54d9 Enable support for vector sext and trunc:
Limit the folding of any_ext and sext  into the load operation to scalars.
Limit the active-bits trunc optimization to scalars.
Document vector trunc and vector sext in LangRef.

Similar to commit 126080 (for enabling zext).



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126424 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-24 21:01:34 +00:00
Devang Patel
3fe3424a21 Move arch specific tests in arch specific directories.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126401 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-24 19:06:27 +00:00