6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-15 20:29:48 +00:00
Code Issues Projects Releases Wiki Activity
98,524 Commits 39 Branches 0 Tags 277 MiB
11b11d77ee
Commit Graph

1072 Commits

Author SHA1 Message Date
Andrea Di Biagio
a29b054e7a Added new X86 patterns to select SSE scalar fp arithmetic instructions from 
a vector packed single/double fp operation followed by a vector insert.

The effect is that the backend coverts the packed fp instruction
followed by a vectro insert into a SSE or AVX scalar fp instruction.

For example, given the following code:
   __m128 foo(__m128 A, __m128 B) {
     __m128 C = A + B;
     return (__m128) {c[0], a[1], a[2], a[3]};
   }

 previously we generated:
   addps %xmm0, %xmm1
   movss %xmm1, %xmm0
 
 we now generate:
   addss %xmm1, %xmm0



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197145 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-12-12 11:50:47 +00:00
Andrea Di Biagio
4b3fcc21ec Ensure that the backend no longer emits unnecessary vector insert instructions 
immediately after SSE scalar fp instructions like addss or mulss.

Added patterns to select SSE scalar fp arithmetic instructions from a scalar
fp operation followed by a blend.

For example, given the following code:
  __m128 foo(__m128 A, __m128 B) {
    A[0] += B[0];
    return A;
  }

previously we generated:
  addss %xmm0, %xmm1
  movss %xmm1, %xmm0

now we generate:
  addss %xmm1, %xmm0



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@196925 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-12-10 15:22:48 +00:00
Cameron McInally
0e6ec124d5 Add an intrinsic for the SSE2 PAUSE instruction. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@195697 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-11-26 00:20:43 +00:00
Cameron McInally
c5a925c198 Fix assembly operands for the SSE2 cvtsd2ss instruction. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@195129 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-11-19 14:36:00 +00:00
Craig Topper
f6157f00db Lift alignment restrictions on load folding for a significant portion of AVX instructions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194048 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-11-05 06:31:43 +00:00
Michael Liao
9d293f1f68 Fix PR17764 
- When selecting BLEND from vselect, the operands need swapping as due to the
  difference between vselect and SSE/AVX's BLEND insn



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193900 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-11-02 00:10:02 +00:00
Benjamin Kramer
bb41c75ab5 X86: Custom lower sext v16i8 to v16i16, and the corresponding truncate. 
Also update the cost model.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193270 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-23 21:06:07 +00:00
Benjamin Kramer
7377cff9e7 X86: Custom lower zext v16i8 to v16i16. 
On sandy bridge (PR17654) we now get
	vpxor	%xmm1, %xmm1, %xmm1
	vpunpckhbw	%xmm1, %xmm0, %xmm2
	vpunpcklbw	%xmm1, %xmm0, %xmm0
	vinsertf128	$1, %xmm2, %ymm0, %ymm0

On haswell it's a simple
	vpmovzxbw	%xmm0, %ymm0

There is a maze of duplicated and dead transforms and patterns in this
area. Remove the dead custom lowering of zext v8i16 to v8i32, that's
already handled by LowerAVXExtend.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193262 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-23 19:19:04 +00:00
Craig Topper
fc678719d9 Replace (V)MOVZDI2PDIrr/rm instructions with patterns that select (V)MOVDI2PDIrr/rm. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193146 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-22 04:35:20 +00:00
Lang Hames
1d82537762 X86 vector element shift-by-immediate instructions take i8 immediates. Make 
the instruction defenitions and ISEL reflect this.

Prior to this patch these instructions took an i32i8imm, and the high bits were
dropped during encoding. This led to incorrect behavior for shifts by
immediates higher than 255. This patch fixes that issue by detecting large
immediate shifts and returning constant zero (for logical shifts) or capping
the shift amount at an encodable value (for arithmetic shifts).

Fixes <rdar://problem/14968098>



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193096 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-21 17:51:24 +00:00
Craig Topper
390ff499f0 Remove x86_sse42_crc32_64_8 intrinsic. It has no functional difference from x86_sse42_crc32_32_8 and was not mapped to a clang builtin. I'm not even sure why this form of the instruction is even called out explicitly in the docs. Also add AutoUpgrade support to convert it into the other intrinsic with appropriate trunc and zext. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192672 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-15 05:20:47 +00:00
Craig Topper
f50045e90d Create classes to reduce the size of the tablegen entries for the CRC32 instructions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192568 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-14 05:19:58 +00:00
Craig Topper
c6f7c99809 Allow pinsrw/pinsrb/pextrb/pextrw/movmskps/movmskpd/pmovmskb/extractps instructions to parse either GR32 or GR64 without resorting to duplicating instructions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192567 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-14 04:55:01 +00:00
Craig Topper
8e121843c1 Add disassembler support for SSE4.1 register/register form of PEXTRW. There is a shorter encoding that was part of SSE2, but a memory form was added in SSE4.1. This is the register form of that encoding. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192566 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-14 01:42:32 +00:00
Craig Topper
bae9f69d37 Mark MOVMSKPS/MOVMSKPD/VPINSRWrr64i as AsmParserOnly to remove them from the disassembler tables. Add PINSRWrr64i to complement the AVX version. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192565 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-14 01:21:22 +00:00
Craig Topper
eefca96792 Don't use 64-bit versions of MOVMSKPD in CodeGen. The instructions only produce a 1-bit result so we can just use SUBREG_TO_REG to extend the 32-bit versions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192562 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-14 00:24:33 +00:00
Craig Topper
c429b5cca1 Mark some more instructions as CodeGenOnly. Remove filters from the disassembler. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192522 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-12 04:46:18 +00:00
Craig Topper
15de63cfde Allow non-AVX form of pmovmskb to take a GR64 operand. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192341 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-10 05:33:31 +00:00
Craig Topper
369cc505e0 Remove duplicate instructions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192340 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-10 05:01:22 +00:00
Elena Demikhovsky
50dc2ad46c AVX-512: Added VRCP28 and VRSQRT28 instructions and intrinsics. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192283 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-09 08:16:14 +00:00
Craig Topper
442b23a817 Mark some instructions as CodeGenOnly since they aren't needed by the assembler or disassembler. Disassembler already filtered them, but asm parser still had them in its tables. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192271 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-09 03:56:16 +00:00
Craig Topper
b96a393b09 Add in64BitMode/in32BitMode to the MMX/SSE2/AVX maskmovq/dq instructions. This way the asm parser will pick the right one based on the mode. Instruction selection already did the right thing based on the pointer size. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192266 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-09 02:18:34 +00:00
Craig Topper
b9bc43852c Remove some instructions that existed to provide aliases to the assembler. Can be done with InstAlias instead. Unfortunately, this was causing printer to use 'vmovq' or 'vmovd' based on what was parsed. To cleanup the inconsistencies convert all 'vmovd' with 64-bit registers to 'vmovq', but provide an alias so that 'vmovd' will still parse. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192171 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-08 05:53:50 +00:00
Craig Topper
e778f82a1e Remove some instructions that seem to only exist to trick the filtering checks in the disassembler table creation. Just fix up the filter to let the real instruction through instead. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192090 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-07 07:19:47 +00:00
Craig Topper
510fb362a8 Remove FsMOVAPSrr and friends. They have no patterns and are no longer selected anywhere. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192089 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-07 06:10:45 +00:00
Craig Topper
8fdba75d5b Teach X86 asm parser that VMOVAPSrr and other VEX-encoded register to register moves should be switched from using the MRMSrcReg form to the MRMDestReg form if the source register is a 64-bit extended register and the destination register is not. 
This allows the instruction to be encoded using the 2-byte VEX form instead of the 3-byte VEX form. The GNU assembler has similar behavior and instruction selection already does this.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192088 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-10-07 05:42:48 +00:00
Craig Topper
1f31a3794e Switch HasAVX to UseAVX in one spot to ensure that AVX512 form of VINSERTPS is used in AVX512 mode. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191489 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-27 07:16:24 +00:00
Craig Topper
11989c2685 Removal some duplicate patterns. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191488 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-27 07:11:17 +00:00
Yunzhong Gao
d7f5fac111 Fixing Intel format of the vshufpd instruction. 
Phabricator code review is located at: http://llvm-reviews.chandlerc.com/D1759



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191481 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-27 01:44:23 +00:00
Craig Topper
333983d0c2 Lift alignment restrictions on load/store folding of VEXTRACTI128/VINSERTI128. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191073 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-20 05:37:49 +00:00
Craig Topper
4acd20a20b Lift alignment restrictions for load/store folding on VINSERTF128/VEXTRACTF128. Fixes PR17268. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190916 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-18 03:55:53 +00:00
Ben Langmuir
215585920f Add llvm.x86.* intrinsics for Intel SHA Extensions 
Add llvm.x86.* intrinsics for all of the Intel SHA Extensions instructions, as
well as tests. Also remove mayLoad and hasSideEffects, which can be inferred
from the instruction patterns.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190864 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-17 13:44:39 +00:00
Craig Topper
5fefc00bac Make F16C feature flag imply AVX rather than just checking both at the patterns. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190775 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-16 04:29:58 +00:00
Ben Langmuir
a247e9d42b Add the remaining Intel SHA instructions 
Also assembly/disassembly tests, and for sha256rnds2, aliases with an explicit
xmm0 dependency.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190754 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-14 15:03:21 +00:00
Preston Gurd
94dc6540a8 Adds support for Atom Silvermont (SLM) - -march=slm 
Implements Instruction scheduler latencies for Silvermont,
using latencies from the Intel Silvermont Optimization Guide.

Auto detects SLM.

Turns on post RA scheduler when generating code for SLM.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190717 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-13 19:23:28 +00:00
Ben Langmuir
1f1bd9a54d Partial support for Intel SHA Extensions (sha1rnds4) 
Add basic assembly/disassembly support for the first Intel SHA
instruction 'sha1rnds4'. Also includes feature flag, and test cases.

Support for the remaining instructions will follow in a separate patch.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190611 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-12 15:51:31 +00:00
Elena Demikhovsky
f9d2d2dc89 AVX-512: implemented extractelement with variable index. 
Added parsing of mask register and "zeroing" semantic, like {%k1} {z}.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190595 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-12 08:55:00 +00:00
Craig Topper
704e8d41fe Add neverHasSideEffects=1 on a couple move instructions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190259 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-09-08 00:50:45 +00:00
Elena Demikhovsky
2fb982aa72 AVX-512: added SQRT, VRSQRT14, VCOMISS, VUCOMISS, VRCP14, VPABS 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189472 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-28 11:21:58 +00:00
Elena Demikhovsky
d371d4f0f4 AVX-512: added conversion instructions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189349 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-27 13:54:04 +00:00
Elena Demikhovsky
92bfb54770 AVX-512: Added shuffle instructions - 
VPSHUFD, VPERMILPS, VMOVDDUP, VMOVLHPS, VMOVHLPS, VSHUFPS, VALIGN
 single and double forms.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189215 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-26 12:45:35 +00:00
Elena Demikhovsky
38cd21a3e9 AVX-512: Added more patterns for VMOVSS, VMOVSD, VMOVD, VMOVQ 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@188786 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-20 11:00:29 +00:00
Craig Topper
b5e1d5b46f Move AVX and non-AVX replication inside a couple multiclasses to avoid repeating each instruction for both individually. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@188743 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-20 04:24:14 +00:00
Elena Demikhovsky
3491d67d3a AVX-512: Added VMOVD, VMOVQ, VMOVSS, VMOVSD instructions. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@188637 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-18 13:08:57 +00:00
Benjamin Kramer
75311b7b4d X86: Turn fp selects into mask operations. 
double test(double a, double b, double c, double d) { return a<b ? c : d; }

before:
_test:
	ucomisd	%xmm0, %xmm1
	ja	LBB0_2
	movaps	%xmm3, %xmm2
LBB0_2:
	movaps	%xmm2, %xmm0

after:
_test:
	cmpltsd	%xmm1, %xmm0
	andpd	%xmm0, %xmm2
	andnpd	%xmm3, %xmm0
	orpd	%xmm2, %xmm0

Small speedup on Benchmarks/SmallPT

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187706 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-04 12:05:16 +00:00
Elena Demikhovsky
f3e3417e65 AVX-512 set: added VEXTRACTPS instruction 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187705 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-08-04 10:46:07 +00:00
Elena Demikhovsky
8395251c0a Added INSERT and EXTRACT intructions from AVX-512 ISA. 
All insertf*/extractf* functions replaced with insert/extract since we have insertf and inserti forms.
Added lowering for INSERT_VECTOR_ELT / EXTRACT_VECTOR_ELT for 512-bit vectors.
Added lowering for EXTRACT/INSERT subvector for 512-bit vectors.
Added a test.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187491 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-07-31 11:35:14 +00:00
Craig Topper
418eb3df74 Changed register names (and pointer keywords) to be lower case when using Intel X86 assembler syntax. 
Patch by Richard Mitton.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187476 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-07-31 02:47:52 +00:00
Craig Topper
9564c1e9b8 Remove some errant space charcters in mnemonic strings. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186932 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-07-23 06:45:34 +00:00
Craig Topper
1011c13f15 More Intel syntax alias fixes. 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186814 91177308-0d34-0410-b5e6-96231b3b80d8
 2013-07-22 09:58:07 +00:00