diff options
| author | Hal Finkel <hfinkel@anl.gov> | 2012-02-01 03:51:43 +0000 |
|---|---|---|
| committer | Hal Finkel <hfinkel@anl.gov> | 2012-02-01 03:51:43 +0000 |
| commit | de5e5ec3045a73a06b1054417f9ac6c02929e9ce (patch) | |
| tree | 02f43070729c0328db2d86e33acd94df3ab52d53 /test/Transforms/BBVectorize/search-limit.ll | |
| parent | d0e277d272d517ca1cda368267d199f0da7cad95 (diff) | |
| download | llvm-de5e5ec3045a73a06b1054417f9ac6c02929e9ce.tar.gz llvm-de5e5ec3045a73a06b1054417f9ac6c02929e9ce.tar.bz2 llvm-de5e5ec3045a73a06b1054417f9ac6c02929e9ce.tar.xz | |
Add a basic-block autovectorization pass.
This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure.
Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149468 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/BBVectorize/search-limit.ll')
| -rw-r--r-- | test/Transforms/BBVectorize/search-limit.ll | 46 |
1 files changed, 46 insertions, 0 deletions
diff --git a/test/Transforms/BBVectorize/search-limit.ll b/test/Transforms/BBVectorize/search-limit.ll new file mode 100644 index 0000000000..d9945b5630 --- /dev/null +++ b/test/Transforms/BBVectorize/search-limit.ll @@ -0,0 +1,46 @@ +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" +; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s +; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-search-limit=4 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-SL4 + +define double @test1(double %A1, double %A2, double %B1, double %B2) { +; CHECK: @test1 +; CHECK-SL4: @test1 +; CHECK-SL4-NOT: <2 x double> +; CHECK: %X1.v.i1.1 = insertelement <2 x double> undef, double %B1, i32 0 +; CHECK: %X1.v.i0.1 = insertelement <2 x double> undef, double %A1, i32 0 +; CHECK: %X1.v.i1.2 = insertelement <2 x double> %X1.v.i1.1, double %B2, i32 1 +; CHECK: %X1.v.i0.2 = insertelement <2 x double> %X1.v.i0.1, double %A2, i32 1 + %X1 = fsub double %A1, %B1 + %X2 = fsub double %A2, %B2 +; CHECK: %X1 = fsub <2 x double> %X1.v.i0.2, %X1.v.i1.2 + %Y1 = fmul double %X1, %A1 + %Y2 = fmul double %X2, %A2 +; CHECK: %Y1 = fmul <2 x double> %X1, %X1.v.i0.2 + %Z1 = fadd double %Y1, %B1 + ; Here we have a dependency chain: the short search limit will not + ; see past this chain and so will not see the second part of the + ; pair to vectorize. + %mul41 = fmul double %Z1, %Y2 + %sub48 = fsub double %Z1, %mul41 + %mul62 = fmul double %Z1, %sub48 + %sub69 = fsub double %Z1, %mul62 + %mul83 = fmul double %Z1, %sub69 + %sub90 = fsub double %Z1, %mul83 + %mul104 = fmul double %Z1, %sub90 + %sub111 = fsub double %Z1, %mul104 + %mul125 = fmul double %Z1, %sub111 + %sub132 = fsub double %Z1, %mul125 + %mul146 = fmul double %Z1, %sub132 + %sub153 = fsub double %Z1, %mul146 + ; end of chain. + %Z2 = fadd double %Y2, %B2 +; CHECK: %Z1 = fadd <2 x double> %Y1, %X1.v.i1.2 + %R1 = fdiv double %Z1, %Z2 + %R = fmul double %R1, %sub153 +; CHECK: %Z1.v.r1 = extractelement <2 x double> %Z1, i32 0 +; CHECK: %Z1.v.r2 = extractelement <2 x double> %Z1, i32 1 +; CHECK: %R1 = fdiv double %Z1.v.r1, %Z1.v.r2 + ret double %R +; CHECK: ret double %R +} + |