mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-01 19:29:22 +00:00
- The fix to PR17631 fixes part of the cases where 'vzeroupper' should not be issued before 'call' insn. There're other cases where helper calls will be inserted not limited to epilog. These helper calls do not follow the standard calling convention and won't clobber any YMM registers. (So far, all call conventions will clobber any or part of YMM registers.) This patch enhances the previous fix to cover more cases 'vzerosupper' should not be inserted by checking if that function call won't clobber any YMM registers and skipping it if so. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@196261 91177308-0d34-0410-b5e6-96231b3b80d8
35 lines
805 B
LLVM
35 lines
805 B
LLVM
; RUN: llc < %s -mcpu=core-avx-i -mtriple=i386-pc-win32 | FileCheck %s
|
|
|
|
%struct_type = type { [64 x <8 x float>], <8 x float> }
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare i32 @llvm.x86.avx.movmsk.ps.256(<8 x float>)
|
|
|
|
; Function Attrs: nounwind
|
|
define i32 @equal(<8 x i32> %A) {
|
|
allocas:
|
|
%first_alloc = alloca [64 x <8 x i32>]
|
|
%second_alloc = alloca %struct_type
|
|
|
|
%A1 = bitcast <8 x i32> %A to <8 x float>
|
|
%A2 = call i32 @llvm.x86.avx.movmsk.ps.256(<8 x float> %A1)
|
|
ret i32 %A2
|
|
}
|
|
|
|
; CHECK: equal
|
|
; CHECK-NOT: vzeroupper
|
|
; CHECK: _chkstk
|
|
; CHECK: ret
|
|
|
|
define <8 x float> @foo(<8 x float> %y, i64* %p, double %x) {
|
|
%i = fptoui double %x to i64
|
|
store i64 %i, i64* %p
|
|
%ret = fadd <8 x float> %y, %y
|
|
ret <8 x float> %ret
|
|
}
|
|
|
|
; CHECK: foo
|
|
; CHECK-NOT: vzeroupper
|
|
; CHECK: _ftol2
|
|
; CHECK: ret
|