6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-08-21 18:29:46 +00:00
Code Issues Projects Releases Wiki Activity
4a52493457
llvm-6502/test
History
Robert Khasanov 4a52493457 [AVX512] Bring back vector-shuffle lowering support through broadcasts 
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.

Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):

 define   <16 x i32> @_inreg16xi32(i32 %a) {
 ; CHECK-LABEL: _inreg16xi32:
 ; CHECK:       ## BB#0:
-; CHECK-NEXT:    vpbroadcastd %edi, %zmm0
+; CHECK-NEXT:    vmovd %edi, %xmm0
+; CHECK-NEXT:    vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT:    vinserti64x4 $1, %ymm0, %zmm0, %zmm0
 ; CHECK-NEXT:    retq
 %b = insertelement <16 x i32> undef, i32 %a, i32 0
 %c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
 ret <16 x i32> %c
}

Here, 256-bit broadcast was generated instead of 512-bit one.

In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
-  assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220774 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-28 12:28:51 +00:00
..
Analysis [DSE] Remove no-data-layout-only type-based overlap checking 2014-10-17 11:56:00 +00:00
Assembler Delete -std-compile-opts. 2014-10-16 20:00:02 +00:00
Bindings [OCaml] hexagon can't run MCJIT tests, XFAIL it. 2014-10-25 19:01:14 +00:00
Bitcode Revert "Revert "DI: Fold constant arguments into a single MDString"" 2014-10-03 20:01:09 +00:00
BugPoint Revert "Revert "DI: Fold constant arguments into a single MDString"" 2014-10-03 20:01:09 +00:00
CodeGen [AVX512] Bring back vector-shuffle lowering support through broadcasts 2014-10-28 12:28:51 +00:00
DebugInfo Fix PR21189 -- Emit symbol subsection required to debug LLVM-built binaries with VS2012+ 2014-10-24 01:27:45 +00:00
ExecutionEngine [MCJIT] Defer application of AArch64 MachO GOT relocations until resolve time. 2014-10-21 23:41:15 +00:00
Feature Delete -std-compile-opts. 2014-10-16 20:00:02 +00:00
FileCheck
Instrumentation [asan] experimental tracing for indirect calls, llvm part. 2014-10-27 18:13:56 +00:00
Integer
JitListener Revert "Revert "DI: Fold constant arguments into a single MDString"" 2014-10-03 20:01:09 +00:00
Linker Add a test for the -suppress-warnings option. 2014-10-25 01:14:15 +00:00
LTO LTO: Add missing target triple from r218784 2014-10-01 18:49:58 +00:00
MC [AVX512] Add vpermil variable version 2014-10-27 23:08:40 +00:00
Object Handle spaces and quotes in file names in MRI scripts. 2014-10-22 03:10:56 +00:00
Other
TableGen [AVX512] Added intrinsics for VPCMPEQB and VPCMPEQW. 2014-09-30 11:32:22 +00:00
tools PR21189: Teach llvm-readobj to dump bits of COFF symbol subsections required to debug using VS2012+ 2014-10-23 22:25:31 +00:00
Transforms InstCombine: Fix a combine assuming that icmp operands were integers 2014-10-27 05:47:49 +00:00
Unit
Verifier Extend the verifier to validate range metadata on calls and invokes. 2014-10-20 23:52:07 +00:00
YAMLParser
.clang-format
CMakeLists.txt Make llvm-go test dependency optional. 2014-10-23 19:51:40 +00:00
lit.cfg Add llvm-go tool. 2014-10-23 02:33:23 +00:00
lit.site.cfg.in Teach lit to filter the host LDFLAGS down from the build system and into 2014-10-21 00:36:28 +00:00
Makefile Teach lit to filter the host LDFLAGS down from the build system and into 2014-10-21 00:36:28 +00:00
Makefile.tests
TestRunner.sh