diff options
| author | Rafael Espindola <rafael.espindola@gmail.com> | 2014-04-29 20:41:54 +0000 |
|---|---|---|
| committer | Rafael Espindola <rafael.espindola@gmail.com> | 2014-04-29 20:41:54 +0000 |
| commit | 984f2fc09e64f9a96ee36cfbf7acfd6c0fb0c7a9 (patch) | |
| tree | 5b79a02c8bf50d72ae37c2c782e89fbd7d328368 /test/Transforms/InstCombine | |
| parent | 6149bc1e104d56274be18ac2270818cb6bd93091 (diff) | |
| download | llvm-984f2fc09e64f9a96ee36cfbf7acfd6c0fb0c7a9.tar.gz llvm-984f2fc09e64f9a96ee36cfbf7acfd6c0fb0c7a9.tar.bz2 llvm-984f2fc09e64f9a96ee36cfbf7acfd6c0fb0c7a9.tar.xz | |
Two fixes to the vpermilvar optimization.
The instcomine logic to handle vpermilvar's pd and 256 variants was incorrect.
The _256 variants have indexes into the individual 128 bit lanes and in all
cases it also has to mask out unused bits.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207577 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/InstCombine')
| -rw-r--r-- | test/Transforms/InstCombine/vec_demanded_elts.ll | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/test/Transforms/InstCombine/vec_demanded_elts.ll b/test/Transforms/InstCombine/vec_demanded_elts.ll index a3e978141a..9ae024181b 100644 --- a/test/Transforms/InstCombine/vec_demanded_elts.ll +++ b/test/Transforms/InstCombine/vec_demanded_elts.ll @@ -318,7 +318,7 @@ define <4 x float> @test_vpermilvar_ps(<4 x float> %v) { declare <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>, <8 x i32>) define <8 x float> @test_vpermilvar_ps_256(<8 x float> %v) { ; CHECK-LABEL: @test_vpermilvar_ps_256( -; CHECK: shufflevector <8 x float> %v, <8 x float> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0> +; CHECK: shufflevector <8 x float> %v, <8 x float> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4> %a = tail call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %v, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>) ret <8 x float> %a } @@ -327,15 +327,15 @@ declare <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double>, <2 x i32>) define <2 x double> @test_vpermilvar_pd(<2 x double> %v) { ; CHECK-LABEL: @test_vpermilvar_pd( ; CHECK: shufflevector <2 x double> %v, <2 x double> undef, <2 x i32> <i32 1, i32 0> - %a = tail call <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double> %v, <2 x i32> <i32 1, i32 0>) + %a = tail call <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double> %v, <2 x i32> <i32 2, i32 0>) ret <2 x double> %a } declare <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double>, <4 x i32>) define <4 x double> @test_vpermilvar_pd_256(<4 x double> %v) { ; CHECK-LABEL: @test_vpermilvar_pd_256( -; CHECK: shufflevector <4 x double> %v, <4 x double> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0> - %a = tail call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %v, <4 x i32> <i32 3, i32 2, i32 1, i32 0>) +; CHECK: shufflevector <4 x double> %v, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2> + %a = tail call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %v, <4 x i32> <i32 3, i32 1, i32 2, i32 0>) ret <4 x double> %a } |