Chris Lattner 3dd08734c1 optimize bitcasts from large integers to vector into vector ... element insertion from the pieces that feed into the vector. This handles a pattern that occurs frequently due to code generated for the x86-64 abi. We now compile something like this: struct S { float A, B, C, D; }; struct S g; struct S bar() { struct S A = g; ++A.A; ++A.C; return A; } into all nice vector operations: _bar: ## @bar ## BB#0: ## %entry movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 pshufd $16, %xmm0, %xmm0 movss 4(%rax), %xmm2 movss 12(%rax), %xmm3 pshufd $16, %xmm2, %xmm2 unpcklps %xmm2, %xmm0 addss 8(%rax), %xmm1 pshufd $16, %xmm1, %xmm1 pshufd $16, %xmm3, %xmm2 unpcklps %xmm2, %xmm1 ret instead of icky integer operations: _bar: ## @bar movq _g@GOTPCREL(%rip), %rax movss LCPI1_0(%rip), %xmm1 movss (%rax), %xmm0 addss %xmm1, %xmm0 movd %xmm0, %ecx movl 4(%rax), %edx movl 12(%rax), %esi shlq $32, %rdx addq %rcx, %rdx movd %rdx, %xmm0 addss 8(%rax), %xmm1 movd %xmm1, %eax shlq $32, %rsi addq %rax, %rsi movd %rsi, %xmm1 ret This resolves rdar://8360454 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112343 91177308-0d34-0410-b5e6-96231b3b80d8		2010-08-28 01:20:38 +00:00
..
Analysis	refix PR1143 by making basicaa analyze zexts of indices aggresively,	2010-08-18 23:09:49 +00:00
Archive
Assembler
Bindings/Ocaml	Fix vmcore.ml test.	2010-08-20 18:24:35 +00:00
Bitcode	Add alignment arguments to all the NEON load/store intrinsics.	2010-08-27 17:13:24 +00:00
BugPoint	XFAIL this on mingw, following remove_arguments_test.ll.	2010-08-24 20:54:50 +00:00
CodeGen	Completely disable tail calls when fast-isel is enabled, as fast-isel	2010-08-28 00:51:03 +00:00
DebugInfo	Convert DbgInfoPrinter to use errs() instead of outs().	2010-08-20 18:03:05 +00:00
ExecutionEngine
Feature	Extend function-local metadata to be usable as attachments.	2010-08-24 02:24:03 +00:00
FrontendAda
FrontendC	no really, fix the test.	2010-08-27 23:05:54 +00:00
FrontendC++
FrontendFortran
FrontendObjC
FrontendObjC++
Integer
lib
Linker	Reapply r112091 and r111922, support for metadata linking, with a	2010-08-26 15:41:53 +00:00
LLVMC	llvmc: Make syntax more consistent.	2010-08-23 23:21:23 +00:00
MC	X86: Fix misencode of RI64mi8. This fixes OpenSSL / x86_64-apple-darwin10 / clang -O3.	2010-08-25 21:11:02 +00:00
Other	Try to escape the '$'s in these so they reach the underlying 'sh' invocation.	2010-08-23 08:54:19 +00:00
Scripts	Add some win64 coff goodness.	2010-08-17 21:05:54 +00:00
TableGen
Transforms	optimize bitcasts from large integers to vector into vector	2010-08-28 01:20:38 +00:00
Unit
Verifier
CMakeLists.txt
lit.cfg	The %ocamlopt setting has embedded quotes. Copy the entire value instead	2010-08-20 14:19:38 +00:00
lit.site.cfg.in
Makefile
Makefile.tests
site.exp.in
TestRunner.sh