RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity

New machine model for cortex-a9. Schedule for resources and latency.

Browse Source 
Schedule more conservatively to account for stalls on floating point
resources and latency. Use the AGU resource to model latency stalls
since it's shared between FP and LD/ST instructions. This might not be
completely accurate but should work well in practice.

llvm-svn: 198125
This commit is contained in:
Andrew Trick 2013-12-28 21:57:05 +00:00
parent 2eb5d59199
commit ed2d925c84
2 changed files with 23 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lib/Target/ARM/ARMScheduleA9.td
View File

@ -1902,14 +1902,20 @@ def CortexA9Model : SchedMachineModel {
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
// Define each kind of processor resource and number available. // Define each kind of processor resource and number available.
//
// The AGU unit has BufferSize=1 so that the latency between operations
// that use it are considered to stall other operations.
//
// The FP unit has BufferSize=0 so that it is a hard dispatch
// hazard. No instruction may be dispatched while the unit is reserved.
let SchedModel = CortexA9Model in { let SchedModel = CortexA9Model in {
def A9UnitALU : ProcResource<2>; def A9UnitALU : ProcResource<2>;
def A9UnitMul : ProcResource<1> { let Super = A9UnitALU; } def A9UnitMul : ProcResource<1> { let Super = A9UnitALU; }
def A9UnitAGU : ProcResource<1>; def A9UnitAGU : ProcResource<1> { let BufferSize = 1; }
def A9UnitLS : ProcResource<1>; def A9UnitLS : ProcResource<1>;
def A9UnitFP : ProcResource<1> { let BufferSize = 1; } def A9UnitFP : ProcResource<1> { let BufferSize = 0; }
def A9UnitB : ProcResource<1>; def A9UnitB : ProcResource<1>;
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//

30
test/CodeGen/ARM/saxpy10-a9.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -march=arm -mtriple=thumbv7-apple-ios7.0.0 -float-abi=hard -mcpu=cortex-a9 -disable-post-ra -misched-bench -scheditins=false | FileCheck %s ; RUN: llc < %s -march=arm -mtriple=thumbv7-apple-ios7.0.0 -float-abi=hard -mcpu=cortex-a9 -misched-postra -misched-bench -scheditins=false | FileCheck %s
; ;
; Test MI-Sched suppory latency based stalls on in in-order pipeline ; Test MI-Sched suppory latency based stalls on in in-order pipeline
; using the new machine model. ; using the new machine model.
@ -15,44 +15,44 @@ target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-
; CHECK: vldr ; CHECK: vldr
; CHECK: vldr ; CHECK: vldr
; CHECK: vldr ; CHECK: vldr
; CHECK-NEXT: vmul
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vldr
; CHECK-NEXT: vadd
; CHECK-NEXT: vmul
; CHECK-NEXT: vldr
; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vmul
; CHECK-NEXT: vldr
; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr
; CHECK-NEXT: vmul ; CHECK-NEXT: vmul
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vmul ; CHECK-NEXT: vmul
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vmul ; CHECK-NEXT: vmul
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vmul ; CHECK-NEXT: vmul
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vmul ; CHECK-NEXT: vmul
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vmul ; CHECK-NEXT: vmul
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr
; CHECK-NEXT: vldr
; CHECK-NEXT: vmul
; CHECK-NEXT: vadd
; CHECK-NEXT: vadd
; CHECK-NEXT: vldr ; CHECK-NEXT: vldr
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd
; CHECK-NEXT: vadd ; CHECK-NEXT: vadd