llvm-mirror/test
Chad Rosier 3127a19140 The Neon VCVT (between floating-point and fixed-point, Advanced SIMD)
instructions can be used to match combinations of multiply/divide and VCVT 
(between floating-point and integer, Advanced SIMD).  Basically the VCVT 
immediate operand that specifies the number of fraction bits corresponds to a 
floating-point multiply or divide by the corresponding power of 2.

For example, VCVT (floating-point to fixed-point, Advanced SIMD) can replace a 
combination of VMUL and VCVT (floating-point to integer) as follows:

Example (assume d17 = <float 8.000000e+00, float 8.000000e+00>):
  vmul.f32        d16, d17, d16
  vcvt.s32.f32    d16, d16
becomes:
  vcvt.s32.f32    d16, d16, #3

Similarly, VCVT (fixed-point to floating-point, Advanced SIMD) can replace a 
combinations of VCVT (integer to floating-point) and VDIV as follows:

Example (assume d17 = <float 8.000000e+00, float 8.000000e+00>):
  vcvt.f32.s32    d16, d16
  vdiv.f32        d16, d17, d16
becomes:
  vcvt.f32.s32    d16, d16, #3

llvm-svn: 133813
2011-06-24 19:23:04 +00:00
..
Analysis Remove support for parsing the "type i32" syntax for defining a numbered 2011-06-19 00:03:46 +00:00
Archive Many LLVM tests relies on standard output stream be in the binary mode. Which is not always the case (on Windows in particular). The patch adds a test to verify that the standard output stream is actually in the binary mode. 2011-05-05 18:40:27 +00:00
Assembler Remove support for parsing the "type i32" syntax for defining a numbered 2011-06-19 00:03:46 +00:00
Bindings/Ocaml
Bitcode Remove support for parsing the "type i32" syntax for defining a numbered 2011-06-19 00:03:46 +00:00
BugPoint
CodeGen The Neon VCVT (between floating-point and fixed-point, Advanced SIMD) 2011-06-24 19:23:04 +00:00
DebugInfo Test for previous commit. 2011-06-17 14:16:17 +00:00
ExecutionEngine manually upgrade a bunch of tests to modern syntax, and remove some that 2011-06-17 03:14:27 +00:00
Feature Remove support for parsing the "type i32" syntax for defining a numbered 2011-06-19 00:03:46 +00:00
FrontendAda Will not compile without the spec! 2011-03-31 10:03:32 +00:00
FrontendC remove an unreduced testcase. 2011-06-18 19:12:59 +00:00
FrontendC++ Remove testcase. It's problematic for the buildbots. 2011-06-03 20:43:58 +00:00
FrontendFortran
FrontendObjC Pass -disable-cfi to llc. 2011-05-06 18:01:58 +00:00
FrontendObjC++
Integer Remove support for parsing the "type i32" syntax for defining a numbered 2011-06-19 00:03:46 +00:00
lib
Linker
LLVMC
MC Add support for movntil/movntiq mnemonics. Reported on llvmdev. 2011-06-23 21:07:47 +00:00
Object
Other Move platform-dependent test to appropriate directory. 2011-05-13 19:45:05 +00:00
Scripts
TableGen Teach TableGen to evaluate DAG expressions as set operations. 2011-06-04 04:11:37 +00:00
Transforms PR10180: Fix a instcombine crash with FP vectors. 2011-06-23 20:40:23 +00:00
Unit test/Unit: Fix enable shared test to follow check that we have actually loaded 2011-06-22 20:41:53 +00:00
Verifier stop accepting begin/end around function bodies in the .ll parser, this isn't pascal anymore. 2011-06-17 06:42:57 +00:00
CMakeLists.txt cmake+lit: final cleanup related to the recent churn 2011-06-23 18:00:32 +00:00
lit.cfg lit support for REQUIRES: asserts. 2011-06-22 23:23:19 +00:00
lit.site.cfg.in cmake+lit: handle ENABLE_ASSERTIONS feature properly. 2011-06-23 17:52:36 +00:00
Makefile cmake+lit: handle ENABLE_ASSERTIONS feature properly. 2011-06-23 17:52:36 +00:00
Makefile.tests
site.exp.in
TestRunner.sh