maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[x86] add tests to show missed 64-bit immediate merging 

Tests are slightly modified versions of those written by
Sunita Marathe in D23391.

llvm-svn: 278599
This commit is contained in:
Sanjay Patel 2016-08-13 18:42:14 +00:00
parent f24939b1f4
commit 08c876673e
1 changed files with 54 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
llvm/test/CodeGen/X86/immediate_merging64.ll Normal file
View File

@ -0,0 +1,54 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu | FileCheck %s
; Check that multiple instances of 64-bit constants encodable as
; 32-bit immediates are merged for code size savings.
@g1 = common global i64 0, align 8
@g2 = common global i64 0, align 8
@g3 = common global i64 0, align 8
@g4 = common global i64 0, align 8
; Immediates with multiple users should not be pulled into instructions when
; optimizing for code size.
define void @imm_multiple_users(i64 %l1, i64 %l2, i64 %l3, i64 %l4) optsize {
; CHECK-LABEL: imm_multiple_users:
; CHECK: # BB#0:
; CHECK-NEXT: movq $-1, {{.*}}(%rip)
; CHECK-NEXT: cmpq $-1, %rdx
; CHECK-NEXT: cmovneq %rsi, %rdi
; CHECK-NEXT: movq %rdi, {{.*}}(%rip)
; CHECK-NEXT: movq $-1, %rax
; CHECK-NEXT: # kill: %CL<def> %CL<kill> %RCX<kill>
; CHECK-NEXT: shlq %cl, %rax
; CHECK-NEXT: movq %rax, {{.*}}(%rip)
; CHECK-NEXT: movq $0, {{.*}}(%rip)
; CHECK-NEXT: retq
;
store i64 -1, i64* @g1, align 8
%cmp = icmp eq i64 %l3, -1
%sel = select i1 %cmp, i64 %l1, i64 %l2
store i64 %sel, i64* @g2, align 8
%and = and i64 %l4, 63
%shl = shl i64 -1, %and
store i64 %shl, i64* @g3, align 8
store i64 0, i64* @g4, align 8
ret void
}
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1)
; Inlined memsets requiring multiple same-sized stores should be lowered using
; the register, rather than immediate, form of stores when optimizing for
; code size.
define void @memset_zero(i8* noalias nocapture %D) optsize {
; CHECK-LABEL: memset_zero:
; CHECK: # BB#0:
; CHECK-NEXT: movq $0, 7(%rdi)
; CHECK-NEXT: movq $0, (%rdi)
; CHECK-NEXT: retq
;
tail call void @llvm.memset.p0i8.i64(i8* %D, i8 0, i64 15, i32 1, i1 false)
ret void
}