diff options
| author | Dehao Chen <dehao@google.com> | 2017-05-12 19:29:27 +0000 |
|---|---|---|
| committer | Dehao Chen <dehao@google.com> | 2017-05-12 19:29:27 +0000 |
| commit | 65dd23e273c5ef69e8ae843ee4fd4664a61d95e9 (patch) | |
| tree | 4b9e6e179fbbefa74060b0a71ce457f97b742a8c /llvm/test/CodeGen/X86/vector-bitreverse.ll | |
| parent | 10c64e6aea87a75da6dff41a95ede1935282d71d (diff) | |
| download | bcm5719-llvm-65dd23e273c5ef69e8ae843ee4fd4664a61d95e9.tar.gz bcm5719-llvm-65dd23e273c5ef69e8ae843ee4fd4664a61d95e9.zip | |
Add LiveRangeShrink pass to shrink live range within BB.
Summary: LiveRangeShrink pass moves instruction right after the definition with the same BB if the instruction and its operands all have more than one use. This pass is inexpensive and guarantees optimal live-range within BB.
Reviewers: davidxl, wmi, hfinkel, MatzeB, andreadb
Reviewed By: MatzeB, andreadb
Subscribers: hiraditya, jyknight, sanjoy, skatkov, gberry, jholewinski, qcolombet, javed.absar, krytarowski, atrick, spatel, RKSimon, andreadb, MatzeB, mehdi_amini, mgorny, efriedma, davide, dberlin, llvm-commits
Differential Revision: https://reviews.llvm.org/D32563
llvm-svn: 302938
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-bitreverse.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/vector-bitreverse.ll | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/llvm/test/CodeGen/X86/vector-bitreverse.ll b/llvm/test/CodeGen/X86/vector-bitreverse.ll index 226c0adbaf3..2fb821555db 100644 --- a/llvm/test/CodeGen/X86/vector-bitreverse.ll +++ b/llvm/test/CodeGen/X86/vector-bitreverse.ll @@ -2372,10 +2372,10 @@ define <8 x i64> @test_bitreverse_v8i64(<8 x i64> %a) nounwind { ; AVX512F-NEXT: vporq %zmm1, %zmm2, %zmm1 ; AVX512F-NEXT: vpsrlq $24, %zmm0, %zmm2 ; AVX512F-NEXT: vpandq {{.*}}(%rip){1to8}, %zmm2, %zmm2 -; AVX512F-NEXT: vpsrlq $8, %zmm0, %zmm3 -; AVX512F-NEXT: vpandq {{.*}}(%rip){1to8}, %zmm3, %zmm3 ; AVX512F-NEXT: vporq %zmm1, %zmm2, %zmm1 -; AVX512F-NEXT: vporq %zmm1, %zmm3, %zmm1 +; AVX512F-NEXT: vpsrlq $8, %zmm0, %zmm2 +; AVX512F-NEXT: vpandq {{.*}}(%rip){1to8}, %zmm2, %zmm2 +; AVX512F-NEXT: vporq %zmm1, %zmm2, %zmm1 ; AVX512F-NEXT: vpsllq $8, %zmm0, %zmm2 ; AVX512F-NEXT: vpandq {{.*}}(%rip){1to8}, %zmm2, %zmm2 ; AVX512F-NEXT: vpsllq $24, %zmm0, %zmm3 |
