Jim Grosbach c6058e2462 X86: Constant fold converting vector setcc results to float. ... Since the result of a SETCC for X86 is 0 or -1 in each lane, we can move unary operations, in this case [su]int_to_fp through the mask operation and constant fold the operation away. Generally speaking: UNARYOP(AND(VECTOR_CMP(x,y), constant)) --> AND(VECTOR_CMP(x,y), constant2) where constant2 is UNARYOP(constant). This implements the transform where UNARYOP is [su]int_to_fp. For example, consider the simple function: define <4 x float> @foo(<4 x float> %val, <4 x float> %test) nounwind { %cmp = fcmp oeq <4 x float> %val, %test %ext = zext <4 x i1> %cmp to <4 x i32> %result = sitofp <4 x i32> %ext to <4 x float> ret <4 x float> %result } Before this change, the SSE code is generated as: LCPI0_0: .long 1 ## 0x1 .long 1 ## 0x1 .long 1 ## 0x1 .long 1 ## 0x1 .section __TEXT,__text,regular,pure_instructions .globl _foo .align 4, 0x90 _foo: ## @foo cmpeqps %xmm1, %xmm0 andps LCPI0_0(%rip), %xmm0 cvtdq2ps %xmm0, %xmm0 retq After, the code is improved to: LCPI0_0: .long 1065353216 ## float 1.000000e+00 .long 1065353216 ## float 1.000000e+00 .long 1065353216 ## float 1.000000e+00 .long 1065353216 ## float 1.000000e+00 .section __TEXT,__text,regular,pure_instructions .globl _foo .align 4, 0x90 _foo: ## @foo cmpeqps %xmm1, %xmm0 andps LCPI0_0(%rip), %xmm0 retq The cvtdq2ps has been constant folded away and the floating point 1.0f vector lanes are materialized directly via the ModRM operand of andps. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213342 91177308-0d34-0410-b5e6-96231b3b80d8		2014-07-18 00:40:56 +00:00
..
Analysis	Improve BasicAA CS-CS queries (redux)	2014-07-17 01:28:25 +00:00
Assembler	IR: Add COMDATs to the IR	2014-06-27 18:19:56 +00:00
Bindings
Bitcode	Roundtrip the inalloca bit on allocas through bitcode	2014-07-16 01:34:27 +00:00
BugPoint	llvm/test/BugPoint/compile-custom.ll: Use explicit %python to invoke a test script, compile-custom.ll.py, for shebang-incapable hosts.	2014-07-11 14:44:10 +00:00
CodeGen	X86: Constant fold converting vector setcc results to float.	2014-07-18 00:40:56 +00:00
DebugInfo	MC: correct DWARF header for PE/COFF assembly input	2014-07-17 16:27:44 +00:00
ExecutionEngine	[RuntimeDyld] Replace a crufty old ARM RuntimeDyld test with a new one that uses	2014-07-10 23:29:11 +00:00
Feature	IR: Allow comdats to be applied to globals with internal linkage	2014-07-13 04:56:11 +00:00
FileCheck	Add FileCheck -implicit-check-not option to allow stricter tests without adding too many CHECK-NOTs manually.	2014-07-11 12:39:32 +00:00
Instrumentation	[ASan] Don't instrument load/stores with !nosanitize metadata.	2014-07-17 18:48:12 +00:00
Integer
JitListener
Linker	IR: Add COMDATs to the IR	2014-06-27 18:19:56 +00:00
LTO	Change the default input for llvm-nm to be a.out instead of standard input	2014-06-23 20:27:53 +00:00
MC	[X86] AVX512: Add disassembler support for compressed displacement	2014-07-17 17:04:56 +00:00
Object	Add printing of Mach-O stabs in llvm-nm.	2014-07-17 22:47:16 +00:00
Other	IR: Fold away compares between GV GEPs and GVs	2014-07-04 22:05:26 +00:00
TableGen	[TableGen] Allow shift operators to take bits<n>	2014-07-17 17:04:27 +00:00
tools	llvm-objdump: Handle BSS sections larger than the object file	2014-07-14 16:20:14 +00:00
Transforms	Move ashr optimization from InstCombineShift to InstSimplify.	2014-07-17 06:28:15 +00:00
Unit	Let test/Unit/lit.cfg add config.shlibdir to $PATH on DLL platforms like cygming.	2014-07-04 05:11:55 +00:00
Verifier	IR: Allow comdats to be applied to globals with internal linkage	2014-07-13 04:56:11 +00:00
YAMLParser
.clang-format
CMakeLists.txt
lit.cfg	llvm/test/lit.cfg: Let %python available.	2014-07-11 14:36:39 +00:00
lit.site.cfg.in
Makefile
Makefile.tests
TestRunner.sh