diff options
author | Hal Finkel <hfinkel@anl.gov> | 2014-12-12 23:59:36 +0000 |
---|---|---|
committer | Hal Finkel <hfinkel@anl.gov> | 2014-12-12 23:59:36 +0000 |
commit | 4c6658feb07d4d3f2412c19be6b6a0c36c9fd111 (patch) | |
tree | 1ba09cdc947070281b3c6e09daf17f968d6ce3b7 /llvm/test/CodeGen/PowerPC/rm-zext.ll | |
parent | 9b6097586ccae0528326527e53fa16721c012b74 (diff) | |
download | bcm5719-llvm-4c6658feb07d4d3f2412c19be6b6a0c36c9fd111.tar.gz bcm5719-llvm-4c6658feb07d4d3f2412c19be6b6a0c36c9fd111.zip |
[PowerPC] Add a DAGToDAG peephole to remove unnecessary zero-exts
On PPC64, we end up with lots of i32 -> i64 zero extensions, not only from all
of the usual places, but also from the ABI, which specifies that values passed
are zero extended. Almost all 32-bit PPC instructions in PPC64 mode are defined
to do *something* to the higher-order bits, and for some instructions, that
action clears those bits (thus providing a zero-extended result). This is
especially common after rotate-and-mask instructions. Adding an additional
instruction to zero-extend the results of these instructions is unnecessary.
This PPCISelDAGToDAG peephole optimization examines these zero-extensions, and
looks back through their operands to see if all instructions will implicitly
zero extend their results. If so, we convert these instructions to their 64-bit
variants (which is an internal change only, the actual encoding of these
instructions is the same as the original 32-bit ones) and remove the
unnecessary zero-extension (changing where the INSERT_SUBREG instructions are
to make everything internally consistent).
llvm-svn: 224169
Diffstat (limited to 'llvm/test/CodeGen/PowerPC/rm-zext.ll')
-rw-r--r-- | llvm/test/CodeGen/PowerPC/rm-zext.ll | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/PowerPC/rm-zext.ll b/llvm/test/CodeGen/PowerPC/rm-zext.ll new file mode 100644 index 00000000000..1e60d1198bc --- /dev/null +++ b/llvm/test/CodeGen/PowerPC/rm-zext.ll @@ -0,0 +1,32 @@ +; RUN: llc -mcpu=pwr7 < %s | FileCheck %s +target datalayout = "E-m:e-i64:64-n32:64" +target triple = "powerpc64-unknown-linux-gnu" + +; Function Attrs: nounwind readnone +define signext i32 @foo(i32 signext %a) #0 { +entry: + %mul = mul nsw i32 %a, %a + %shr2 = lshr i32 %mul, 5 + ret i32 %shr2 + +; CHECK-LABEL @foo +; CHECK-NOT: rldicl 3, {{[0-9]+}}, 0, 32 +; CHECK: blr +} + +define zeroext i32 @test6(i32 zeroext %x) #0 { +entry: + %and = lshr i32 %x, 16 + %shr = and i32 %and, 255 + %and1 = shl i32 %x, 16 + %shl = and i32 %and1, 16711680 + %or = or i32 %shr, %shl + ret i32 %or + +; CHECK-LABEL @test6 +; CHECK-NOT: rldicl 3, {{[0-9]+}}, 0, 32 +; CHECK: blr +} + +attributes #0 = { nounwind readnone } + |