1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 13:11:39 +01:00
Brendon Cahoon 59f22c6fd7 [Pipeliner] Add two pragmas to control software pipelining optimization
#pragma clang loop pipeline(disable)
  
    Disable SWP optimization for the next loop.
    “disable” is the only possible value.
  
#pragma clang loop pipeline_initiation_interval(number)
  
    Set value of initiation interval for SWP
    optimization to specified number value for
    the next loop. Number is the positive value
    greater than 0.
  
These pragmas could be used for debugging or reducing
compile time purposes. It is possible to disable SWP for
concrete loops to save compilation time or to find bugs
by not doing SWP to certain loops. It is possible to set
value of initiation interval to concrete number to save
compilation time by not doing extra pipeliner passes or
to check created schedule for specific initiation interval.

That is llvm part of the fix

Clang part of fix: https://reviews.llvm.org/D55710

Patch by Alexey Lapshin!

Differential Revision: https://reviews.llvm.org/D56403

llvm-svn: 351923
2019-01-23 03:26:10 +00:00

44 lines
1.2 KiB
LLVM

; RUN: llc -disable-lsr -march=hexagon -enable-pipeliner \
; RUN: -debug-only=pipeliner < %s 2>&1 > /dev/null | FileCheck %s
; REQUIRES: asserts
;
; Test that checks if the ResMII is 1.
; CHECK: MII = 1 MAX_II = 11 (rec=1, res=1)
; Function Attrs: nounwind
define void @f0(i32* nocapture %a0, i32 %a1) #0 {
b0:
%v0 = icmp sgt i32 %a1, 1
br i1 %v0, label %b1, label %b4
b1: ; preds = %b0
%v1 = load i32, i32* %a0, align 4
%v2 = add i32 %v1, 10
%v3 = getelementptr i32, i32* %a0, i32 1
%v4 = add i32 %a1, -1
br label %b2
b2: ; preds = %b2, %b1
%v5 = phi i32 [ %v12, %b2 ], [ %v4, %b1 ]
%v6 = phi i32* [ %v11, %b2 ], [ %v3, %b1 ]
%v7 = phi i32 [ %v10, %b2 ], [ %v2, %b1 ]
store i32 %v7, i32* %v6, align 4
%v8 = add i32 %v7, 10
%v9 = getelementptr i32, i32* %v6, i32 -1
store i32 %v8, i32* %v9, align 4
%v10 = add i32 %v7, 10
%v11 = getelementptr i32, i32* %v6, i32 1
%v12 = add i32 %v5, -1
%v13 = icmp eq i32 %v12, 0
br i1 %v13, label %b3, label %b2
b3: ; preds = %b2
br label %b4
b4: ; preds = %b3, %b0
ret void
}
attributes #0 = { nounwind }