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

Expand and rewrite comment. 

llvm-svn: 189998
This commit is contained in:
Eric Christopher 2013-09-04 21:23:23 +00:00
parent b05db8e0b9
commit 888af62c1b
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/test/CodeGen/ARM/swift-vldm.ll
View File

@ -1,7 +1,8 @@
; RUN: llc < %s -mcpu=swift -mtriple=armv7s-apple-ios | FileCheck %s ; RUN: llc < %s -mcpu=swift -mtriple=armv7s-apple-ios | FileCheck %s
; vldm with registers not aligned with q registers need more micro-ops so that ; Check that we avoid producing vldm instructions using d registers that
; so that there usage becomes unbeneficial on swift. ; begin in the most-significant half of a q register. These require more
; micro-ops on swift and so aren't worth combining.
; CHECK-LABEL: test_vldm ; CHECK-LABEL: test_vldm
; CHECK: vldmia r{{[0-9]+}}, {d2, d3, d4} ; CHECK: vldmia r{{[0-9]+}}, {d2, d3, d4}
@ -19,7 +20,7 @@ entry:
%d2 = load double * %addr1 %d2 = load double * %addr1
%d3 = load double * %addr2 %d3 = load double * %addr2
%d4 = load double * %addr3 %d4 = load double * %addr3
; We are trying to force x[0-3] in register d1 to d4 so that we can test we ; We are trying to force x[0-3] in registers d1 to d4 so that we can test we
; don't form a "vldmia rX, {d1, d2, d3, d4}". ; don't form a "vldmia rX, {d1, d2, d3, d4}".
; We are relying on the calling convention and that register allocation ; We are relying on the calling convention and that register allocation
; properly coalesces registers. ; properly coalesces registers.