mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 13:11:39 +01:00
b2a4fe0946
This patch follows some ideas from r352866 to optimize the floating point materialization even further. It changes isFPImmLegal to considere up to 2 mov instruction or up to 5 in case subtarget has fused literals. The rationale is the cost is the same for mov+fmov vs. adrp+ldr; but the mov+fmov sequence is always better because of the reduced d-cache pressure. The timings are still the same if you consider movw+movk+fmov vs. adrp+ldr will be fused (although one instruction longer). Reviewers: efriedma Differential Revision: https://reviews.llvm.org/D58460 llvm-svn: 356390
41 lines
982 B
LLVM
41 lines
982 B
LLVM
; RUN: llc < %s -mtriple=arm64-apple-darwin | FileCheck %s
|
|
|
|
; CHECK: literal8
|
|
; CHECK: .quad 4614256656552045848
|
|
define double @foo() optsize {
|
|
; CHECK: _foo:
|
|
; CHECK: adrp x[[REG:[0-9]+]], lCPI0_0@PAGE
|
|
; CHECK: ldr d0, [x[[REG]], lCPI0_0@PAGEOFF]
|
|
; CHECK-NEXT: ret
|
|
ret double 0x400921FB54442D18
|
|
}
|
|
|
|
; CHECK: literal8
|
|
; CHECK: .quad 137438953409
|
|
define double @foo2() optsize {
|
|
; CHECK: _foo2:
|
|
; CHECK: adrp x[[REG:[0-9]+]], lCPI1_0@PAGE
|
|
; CHECK: ldr d0, [x[[REG]], lCPI1_0@PAGEOFF]
|
|
; CHECK-NEXT: ret
|
|
ret double 0x1FFFFFFFC1
|
|
}
|
|
|
|
define float @bar() optsize {
|
|
; CHECK: _bar:
|
|
; CHECK: adrp x[[REG:[0-9]+]], lCPI2_0@PAGE
|
|
; CHECK: ldr s0, [x[[REG]], lCPI2_0@PAGEOFF]
|
|
; CHECK-NEXT: ret
|
|
ret float 0x400921FB60000000
|
|
}
|
|
|
|
; CHECK: literal16
|
|
; CHECK: .quad 0
|
|
; CHECK: .quad 0
|
|
define fp128 @baz() optsize {
|
|
; CHECK: _baz:
|
|
; CHECK: adrp x[[REG:[0-9]+]], lCPI3_0@PAGE
|
|
; CHECK: ldr q0, [x[[REG]], lCPI3_0@PAGEOFF]
|
|
; CHECK-NEXT: ret
|
|
ret fp128 0xL00000000000000000000000000000000
|
|
}
|