6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-16 11:30:51 +00:00
Code Issues Projects Releases Wiki Activity
0ab2058852
llvm-6502/test/Transforms/BBVectorize/simple3.ll

36 lines
1.7 KiB
LLVM
Raw Normal View History

Allow BBVectorize to form non-2^n-length vectors. The original algorithm only used recursive pair fusion of equal-length types. This is now extended to allow pairing of any types that share the same underlying scalar type. Because we would still generally prefer the 2^n-length types, those are formed first. Then a second set of iterations form the non-2^n-length types. Also, a call to SimplifyInstructionsInBlock has been added after each pairing iteration. This takes care of DCE (and a few other things) that make the following iterations execute somewhat faster. For the same reason, some of the simple shuffle-combination cases are now handled internally. There is some additional refactoring work to be done, but I've had many requests for this feature, so additional refactoring will come soon in future commits (as will additional test cases). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159330 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-28 05:42:42 +00:00
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
Switch BBVectorize to directly depend on having a TTI analysis. This could be simplified further, but Hal has a specific feature for ignoring TTI, and so I preserved that. Also, I needed to use it because a number of tests fail when switching from a null TTI to the NoTTI nonce implementation. That seems suspicious to me and so may be something that you need to look into Hal. I worked it by preserving the old behavior for these tests with the flag that ignores all target info. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171722 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-07 10:22:36 +00:00
; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-vector-bits=192 -bb-vectorize-ignore-target-info -instcombine -gvn -S | FileCheck %s
Allow BBVectorize to form non-2^n-length vectors. The original algorithm only used recursive pair fusion of equal-length types. This is now extended to allow pairing of any types that share the same underlying scalar type. Because we would still generally prefer the 2^n-length types, those are formed first. Then a second set of iterations form the non-2^n-length types. Also, a call to SimplifyInstructionsInBlock has been added after each pairing iteration. This takes care of DCE (and a few other things) that make the following iterations execute somewhat faster. For the same reason, some of the simple shuffle-combination cases are now handled internally. There is some additional refactoring work to be done, but I've had many requests for this feature, so additional refactoring will come soon in future commits (as will additional test cases). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159330 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-28 05:42:42 +00:00
; Basic depth-3 chain
define double @test1(double %A1, double %A2, double %A3, double %B1, double %B2, double %B3) {
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186268 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-14 01:42:54 +00:00
; CHECK-LABEL: @test1(
Allow BBVectorize to form non-2^n-length vectors. The original algorithm only used recursive pair fusion of equal-length types. This is now extended to allow pairing of any types that share the same underlying scalar type. Because we would still generally prefer the 2^n-length types, those are formed first. Then a second set of iterations form the non-2^n-length types. Also, a call to SimplifyInstructionsInBlock has been added after each pairing iteration. This takes care of DCE (and a few other things) that make the following iterations execute somewhat faster. For the same reason, some of the simple shuffle-combination cases are now handled internally. There is some additional refactoring work to be done, but I've had many requests for this feature, so additional refactoring will come soon in future commits (as will additional test cases). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159330 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-28 05:42:42 +00:00
; CHECK: %X1.v.i1.11 = insertelement <3 x double> undef, double %B1, i32 0
; CHECK: %X1.v.i1.22 = insertelement <3 x double> %X1.v.i1.11, double %B2, i32 1
; CHECK: %X1.v.i1 = insertelement <3 x double> %X1.v.i1.22, double %B3, i32 2
; CHECK: %X1.v.i0.13 = insertelement <3 x double> undef, double %A1, i32 0
; CHECK: %X1.v.i0.24 = insertelement <3 x double> %X1.v.i0.13, double %A2, i32 1
; CHECK: %X1.v.i0 = insertelement <3 x double> %X1.v.i0.24, double %A3, i32 2
%X1 = fsub double %A1, %B1
%X2 = fsub double %A2, %B2
%X3 = fsub double %A3, %B3
; CHECK: %X1 = fsub <3 x double> %X1.v.i0, %X1.v.i1
%Y1 = fmul double %X1, %A1
%Y2 = fmul double %X2, %A2
%Y3 = fmul double %X3, %A3
; CHECK: %Y1 = fmul <3 x double> %X1, %X1.v.i0
%Z1 = fadd double %Y1, %B1
%Z2 = fadd double %Y2, %B2
%Z3 = fadd double %Y3, %B3
; CHECK: %Z1 = fadd <3 x double> %Y1, %X1.v.i1
%R1 = fmul double %Z1, %Z2
%R = fmul double %R1, %Z3
; CHECK: %Z1.v.r210 = extractelement <3 x double> %Z1, i32 2
; CHECK: %Z1.v.r1 = extractelement <3 x double> %Z1, i32 0
; CHECK: %Z1.v.r2 = extractelement <3 x double> %Z1, i32 1
; CHECK: %R1 = fmul double %Z1.v.r1, %Z1.v.r2
; CHECK: %R = fmul double %R1, %Z1.v.r210
ret double %R
; CHECK: ret double %R
}
Reference in New Issue Copy Permalink