mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 04:22:57 +02:00
cdae83c48c
Re-comitting with a change that avoids undefined uses getting put into the VRegUses list. The new algorithm remembers the uses encountered while walking backwards until a matching def is found. Contrary to the previous version this: - Works without LiveIntervals being available - Allows to increase the precision to subregisters/lanemasks (not used for now) The changes in the AMDGPU tests are necessary because the R600 scheduler is not stable with respect to the order of nodes in the ready queues. Differential Revision: http://reviews.llvm.org/D9068 llvm-svn: 254683
18 lines
621 B
LLVM
18 lines
621 B
LLVM
; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=R600 %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=SI %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefix=SI %s
|
|
|
|
; R600: {{^}}amdgpu_trunc:
|
|
; R600: TRUNC {{\*? *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z
|
|
; SI: {{^}}amdgpu_trunc:
|
|
; SI: v_trunc_f32
|
|
|
|
define void @amdgpu_trunc(float addrspace(1)* %out, float %x) {
|
|
entry:
|
|
%0 = call float @llvm.AMDGPU.trunc(float %x)
|
|
store float %0, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.AMDGPU.trunc(float ) readnone
|