diff options
| author | Gadi Haber <gadi.haber@intel.com> | 2016-12-28 10:12:48 +0000 |
|---|---|---|
| committer | Gadi Haber <gadi.haber@intel.com> | 2016-12-28 10:12:48 +0000 |
| commit | 19c4fc5e62905006dfcee26ade7dbada2c90fae9 (patch) | |
| tree | 049e45129d9006aec0e1c1f7943316abcbc9092a /llvm/lib/Target/X86/InstPrinter | |
| parent | b9565705bdc917800a4298473be4a69273abe514 (diff) | |
| download | bcm5719-llvm-19c4fc5e62905006dfcee26ade7dbada2c90fae9.tar.gz bcm5719-llvm-19c4fc5e62905006dfcee26ade7dbada2c90fae9.zip | |
This is a large patch for X86 AVX-512 of an optimization for reducing code size by encoding EVEX AVX-512 instructions using the shorter VEX encoding when possible.
There are cases of AVX-512 instructions that have two possible encodings. This is the case with instructions that use vector registers with low indexes of 0 - 15 and do not use the zmm registers or the mask k registers.
The EVEX encoding prefix requires 4 bytes whereas the VEX prefix can take only up to 3 bytes. Consequently, using the VEX encoding for these instructions results in a code size reduction of ~2 bytes even though it is compiled with the AVX-512 features enabled.
Reviewers: Craig Topper, Zvi Rackoover, Elena Demikhovsky
Differential Revision: https://reviews.llvm.org/D27901
llvm-svn: 290663
Diffstat (limited to 'llvm/lib/Target/X86/InstPrinter')
| -rw-r--r-- | llvm/lib/Target/X86/InstPrinter/X86InstComments.h | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/InstPrinter/X86InstComments.h b/llvm/lib/Target/X86/InstPrinter/X86InstComments.h index 687581b10ae..c6d0d85a7d3 100644 --- a/llvm/lib/Target/X86/InstPrinter/X86InstComments.h +++ b/llvm/lib/Target/X86/InstPrinter/X86InstComments.h @@ -16,6 +16,11 @@ #define LLVM_LIB_TARGET_X86_INSTPRINTER_X86INSTCOMMENTS_H namespace llvm { + + enum AsmComments { + AC_EVEX_2_VEX = 0x2 // For instr that was compressed from EVEX to VEX. + }; + class MCInst; class raw_ostream; bool EmitAnyX86InstComments(const MCInst *MI, raw_ostream &OS, |
