stan/jdk-24
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
12,623 Commits 2 Branches 0 Tags
Commit Graph

60 Commits

Author SHA1 Message Date
Roland Westrelin
b305cf722e 7133857: exp() and pow() should use the x87 ISA on x86 
Use x87 instructions to implement exp() and pow() in interpreter/c1/c2.

Reviewed-by: kvn, never, twisti
 2012-05-15 10:10:23 +02:00
Nils Eliasson
7b7d3507db 7152957: VM crashes with assert(false) failed: bad AD file 
Reviewed-by: kvn, never
 2012-03-12 15:28:07 -07:00
Vladimir Kozlov
867f3ba889 7145346: VerifyStackAtCalls is broken 
Replace call_epilog() encoding with macroassembler use. Moved duplicated code to x86.ad. Fixed return_addr() definition.

Reviewed-by: never
 2012-02-16 17:12:49 -08:00
Vladimir Kozlov
539616f85a 7125136: SIGILL on linux amd64 in gc/ArrayJuggle/Juggle29 
For C2 moved saving EBP after ESP adjustment. For C1 generated 5 byte nop instruction first if needed.

Reviewed-by: never, twisti, azeemj
 2012-02-15 21:37:49 -08:00
Vladimir Kozlov
94927c382b 7125896: Eliminate nested locks 
Nested locks elimination done before lock nodes expansion by looking for outer locks of the same object.

Reviewed-by: never, twisti
 2012-01-07 13:26:43 -08:00
Roland Westrelin
97439fb4ff 7121140: Allocation paths require explicit memory synchronization operations for RMO systems 
Adds store store barrier after initialization of header and body of objects.

Reviewed-by: never, kvn
 2011-12-20 16:56:50 +01:00
Vladimir Kozlov
dc542c9909 7121648: Use 3-operands SIMD instructions on x86 with AVX 
Use 3-operands SIMD instructions in C2 generated code for machines with AVX.

Reviewed-by: never
 2011-12-20 00:55:02 -08:00
Vladimir Kozlov
b7f5d60a7e 7116452: Add support for AVX instructions 
Added support for AVX extension to the x86 instruction set.

Reviewed-by: never
 2011-12-14 14:54:38 -08:00
Roland Westrelin
07d9df5a7f 7090968: Allow adlc register class to depend on runtime conditions 
Allow reg_class definition as a function.

Reviewed-by: kvn, never
 2011-11-22 09:45:57 +01:00
Christian Thalinger
81c085a1e2 7003454: order constants in constant table by number of references in code 
Reviewed-by: kvn, never, bdelsart
 2011-11-16 01:39:50 -08:00
Vladimir Kozlov
669fa7396d 7097546: Optimize use of CMOVE instructions 
Avoid CMove in a loop if possible. May generate CMove if it could be moved outside a loop.

Reviewed-by: never
 2011-10-26 06:08:56 -07:00
Vladimir Kozlov
90651b2666 7079329: Adjust allocation prefetching for T4 
On T4 2 BIS instructions should be issued to prefetch 64 bytes

Reviewed-by: iveresov, phh, twisti
 2011-08-16 16:59:46 -07:00
Vladimir Kozlov
ac99f413d7 7063629: use cbcond in C2 generated code on T4 
Use new short branch instruction in C2 generated code.

Reviewed-by: never
 2011-08-11 12:08:11 -07:00
Roland Westrelin
b543a07b9a 7074017: Introduce MemBarAcquireLock/MemBarReleaseLock nodes for monitor enter/exit code paths 
Replace MemBarAcquire/MemBarRelease nodes on the monitor enter/exit code paths with new MemBarAcquireLock/MemBarReleaseLock nodes

Reviewed-by: kvn, twisti
 2011-08-02 18:36:40 +02:00
Vladimir Kozlov
18329266ea 7069452: Cleanup NodeFlags 
Remove flags which duplicate information in Node::NodeClasses.

Reviewed-by: never
 2011-07-27 17:28:36 -07:00
Vladimir Kozlov
48c1293916 7063628: Use cbcond on T4 
Add new short branch instruction to Hotspot sparc assembler.

Reviewed-by: never, twisti, jrose
 2011-07-21 11:25:07 -07:00
Vladimir Kozlov
1ac79543d0 5091921: Sign flip issues in loop optimizer 
Fix integer overflow problem in the code generated by loop optimizer.

Reviewed-by: never
 2011-05-04 13:12:42 -07:00
Tom Deneau
899faa3fec 7035713: 3DNow Prefetch Instruction Support 
The upcoming processors from AMD are the first that support 3dnow prefetch without supporting the 3dnow instruction set.

Reviewed-by: kvn
 2011-04-11 15:30:31 -07:00
Roland Westrelin
4171ca786e 7029017: Additional architecture support for c2 compiler 
Enables cross building of a c2 VM. Support masking of shift counts when the processor architecture mandates it.

Reviewed-by: kvn, never
 2011-03-25 09:35:39 +01:00
Vladimir Kozlov
a74bc73598 6942326: x86 code in string_indexof() could read beyond reserved heap space 
Copy small (<8) strings on stack if str+16 crosses a page boundary and load from stack into XMM. Back up pointer when loading string's tail.

Reviewed-by: never
 2011-02-26 12:10:54 -08:00
Tom Rodriguez
4b3ada699d 7016474: string compare intrinsic improvements 
Reviewed-by: kvn
 2011-02-09 15:02:23 -08:00
Christian Thalinger
ffaadcecea 6961690: load oops from constant table on SPARC 
Oops should be loaded from the constant table of an nmethod instead of materializing them with a long code sequence.

Reviewed-by: never, kvn
 2010-12-03 01:34:31 -08:00
Vladimir Kozlov
ce2df719c6 6997311: SIGFPE in new long division asm code 
Use unsigned DIV instruction

Reviewed-by: never
 2010-11-06 18:52:07 -07:00
Vladimir Kozlov
249b1f6c4f 6987135: Performance regression on Intel platform with 32-bits edition between 6u13 and 6u14 
Use hardware DIV instruction for long division by constant when it is faster than code with multiply.

Reviewed-by: never
 2010-11-02 09:00:37 -07:00
Christian Thalinger
a4b2fe3b1c 6978355: renaming for 6961697 
This is the renaming part of 6961697 to keep the actual changes small for review.

Reviewed-by: kvn, never
 2010-08-25 05:27:54 -07:00
Tom Rodriguez
a54b1ff70e 6978249: spill between cpu and fpu registers when those moves are fast 
Reviewed-by: kvn
 2010-08-19 14:51:47 -07:00
John R Rose
d6a9b93b5a Merge 2010-06-02 22:45:42 -07:00
Vladimir Kozlov
a3005a16fc 6954029: Improve implicit null check generation with compressed oops 
Hoist DecodeN instruction above null check

Reviewed-by: never, twisti
 2010-06-02 09:49:32 -07:00
Erik Trimble
ba7c173659 6941466: Oracle rebranding changes for Hotspot repositories 
Change all the Sun copyrights to Oracle copyright

Reviewed-by: ohair
 2010-05-27 19:08:38 -07:00
Christian Thalinger
7a9f2e7625 6934104: JSR 292 needs to support SPARC C2 
C2 for SPARC needs to support JSR 292.

Reviewed-by: kvn, never
 2010-05-25 02:38:48 -07:00
Hiroshi Yamauchi
cd48f31efe 6946040: add intrinsic for short and char reverseBytes 
Reviewed-by: never, twisti
 2010-04-26 11:27:21 -07:00
Vladimir Kozlov
fa2d360cd5 6910664: C2: java/util/Arrays/Sorting.java fails with DeoptimizeALot flag 
Matcher::float_in_double should be true only when FPU is used for floats.

Reviewed-by: never, twisti
 2010-02-19 10:04:16 -08:00
Hiroshi Yamauchi
688398edef 6921969: optimize 64 long multiply for case with high bits zero 
Reviewed-by: never, twisti, kvn, rasbold
 2010-02-03 15:56:37 -08:00
Christian Thalinger
375527d84e 6829187: compiler optimizations required for JSR 292 
C2 implementation for invokedynamic support.

Reviewed-by: kvn, never
 2010-01-05 13:05:58 +01:00
John R Rose
e261aecad8 6863023: need non-perm oops in code cache for JSR 292 
Make a special root-list for those few nmethods which might contain non-perm oops.

Reviewed-by: twisti, kvn, never, jmasa, ysr
 2009-09-15 21:53:47 -07:00
Vladimir Kozlov
243514d483 6827605: new String intrinsics may prevent EA scalar replacement 
6875866: Intrinsic for String.indexOf() is broken on x86 with SSE4.2

Modify String intrinsic methods to pass char[] pointers instead of string oops.

Reviewed-by: never
 2009-09-14 12:14:20 -07:00
Christian Thalinger
a9ad90fa87 5057225: Remove useless I2L conversions 
The optimizer should be told to normalize (AndL (ConvI2L x) 0xFF) to (ConvI2L (AndI x 0xFF)), and then the existing matcher rule will work for free.

Reviewed-by: kvn
 2009-06-26 07:26:10 -07:00
Christian Thalinger
8a262ce04b 6814842: Load shortening optimizations 
6797305 handles load widening but no shortening which should be covered here.

Reviewed-by: never, kvn
 2009-05-13 00:45:22 -07:00
Christian Thalinger
6a270f9f19 6823354: Add intrinsics for {Integer,Long}.{numberOfLeadingZeros,numberOfTrailingZeros}() 
These methods can be instrinsified by using bit scan, bit test, and population count instructions.

Reviewed-by: kvn, never
 2009-05-06 00:27:52 -07:00
Changpeng Fang
c0d62ad9e6 6761600: Use sse 4.2 in intrinsics 
Use SSE 4.2 in intrinsics for String.{compareTo/equals/indexOf} and Arrays.equals.

Reviewed-by: kvn, never, jrose
 2009-03-31 14:07:08 -07:00
Tom Rodriguez
134debb0ba 6822204: volatile fences should prefer lock:addl to actual mfence instructions 
Reviewed-by: kvn, phh
 2009-03-26 14:31:45 -07:00
John R Rose
b8dbe8d8f6 6813212: factor duplicated assembly code for general subclass check (for 6655638) 
Code in interp_masm, stubGenerator, c1_LIRAssembler, and AD files moved into MacroAssembler.

Reviewed-by: kvn
 2009-03-13 18:39:22 -07:00
Christian Thalinger
de67e52949 6378821: bitCount() should use POPC on SPARC processors and AMD+10h 
BitCount() should use POPC on SPARC processors where POPC is implemented directly in hardware.

Reviewed-by: kvn, never
 2009-03-13 11:35:17 -07:00
Christian Thalinger
89cea91c48 6797305: Add LoadUB and LoadUI opcode class 
Add a LoadUB (unsigned byte) and LoadUI (unsigned int) opcode class so we have these load optimizations in the first place and do not need to handle them in the matcher.

Reviewed-by: never, kvn
 2009-03-09 03:17:11 -07:00
John R Rose
07321dec65 6812678: macro assembler needs delayed binding of a few constants (for 6655638) 
Minor assembler enhancements preparing for method handles

Reviewed-by: kvn
 2009-03-04 09:58:39 -08:00
Christian Thalinger
05d1de7727 6810672: Comment typos 
I have collected some typos I have found while looking at the code.

Reviewed-by: kvn, never
 2009-02-27 13:27:09 -08:00
Vladimir Kozlov
681eb89b31 Merge 2009-02-17 14:30:24 -08:00
Christian Thalinger
3b8452da93 6796746: rename LoadC (char) opcode class to LoadUS (unsigned short) 
Renaming LoadC to LoadUS would round up the planned introduction of LoadUB and LoadUI.

Reviewed-by: phh, kvn
 2009-01-26 16:22:12 +01:00
Xiaobin Lu
1362b9fd1d 6787106: Hotspot 32 bit build fails on platforms having different definitions for intptr_t & int32_t 
Avoid casting between int32_t and intptr_t specifically for MasmAssembler::movptr in 32 bit platforms.

Reviewed-by: jrose, kvn
 2008-12-24 13:06:09 -08:00
Vladimir Kozlov
7aae40a95f 6462850: generate biased locking code in C2 ideal graph 
Inline biased locking code in C2 ideal graph during macro nodes expansion

Reviewed-by: never
 2008-11-07 09:29:38 -08:00