mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
2be00d9e54
Current tail duplication integrated in bb layout is designed to increase the fallthrough from a BB's predecessor to its successor, but we have observed cases that duplication doesn't increase fallthrough, or it brings too much size overhead. To overcome these two issues in function canTailDuplicateUnplacedPreds I add two checks: make sure there is at least one duplication in current work set. the number of duplication should not exceed the number of successors. The modification in hasBetterLayoutPredecessor fixes a bug that potential predecessor must be at the bottom of a chain. Differential Revision: https://reviews.llvm.org/D64376
93 lines
2.3 KiB
YAML
93 lines
2.3 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -march=amdgcn -o - -run-pass=block-placement -mcpu=gfx1010 -mattr=-inst-fwd-prefetch-bug -verify-machineinstrs %s | FileCheck -check-prefix=GCN %s
|
|
|
|
# Used to fail with
|
|
# Assertion `Out && "Header of loop has no predecessors from outside loop?"
|
|
|
|
---
|
|
name: loop_header_nopred
|
|
body: |
|
|
; GCN-LABEL: name: loop_header_nopred
|
|
; GCN: bb.0:
|
|
; GCN: successors: %bb.1(0x80000000)
|
|
; GCN: S_INST_PREFETCH 1
|
|
; GCN: S_BRANCH %bb.1
|
|
; GCN: bb.6 (align 64):
|
|
; GCN: successors: %bb.7(0x04000000), %bb.1(0x7c000000)
|
|
; GCN: S_CBRANCH_VCCNZ %bb.7, implicit $vcc
|
|
; GCN: bb.1:
|
|
; GCN: successors: %bb.2(0x40000000), %bb.3(0x40000000)
|
|
; GCN: S_CBRANCH_VCCNZ %bb.2, implicit $vcc
|
|
; GCN: bb.3:
|
|
; GCN: successors: %bb.4(0x40000000), %bb.6(0x40000000)
|
|
; GCN: SI_MASK_BRANCH %bb.6, implicit $exec
|
|
; GCN: S_BRANCH %bb.4
|
|
; GCN: bb.2 (align 64):
|
|
; GCN: successors: %bb.4(0x40000000), %bb.6(0x40000000)
|
|
; GCN: SI_MASK_BRANCH %bb.6, implicit $exec
|
|
; GCN: S_BRANCH %bb.4
|
|
; GCN: bb.4:
|
|
; GCN: successors: %bb.5(0x04000000), %bb.4(0x7c000000)
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_NOP 0
|
|
; GCN: S_CBRANCH_EXECZ %bb.4, implicit $exec
|
|
; GCN: bb.5:
|
|
; GCN: successors: %bb.6(0x80000000)
|
|
; GCN: S_BRANCH %bb.6
|
|
; GCN: bb.7:
|
|
; GCN: S_ENDPGM 0
|
|
bb.0:
|
|
successors: %bb.1(0x80000000)
|
|
|
|
bb.1:
|
|
successors: %bb.2(0x40000000), %bb.3(0x40000000)
|
|
|
|
S_CBRANCH_VCCZ %bb.3, implicit $vcc
|
|
S_BRANCH %bb.2
|
|
|
|
bb.2:
|
|
successors: %bb.3(0x80000000)
|
|
|
|
bb.3:
|
|
successors: %bb.4(0x40000000), %bb.6(0x40000000)
|
|
|
|
SI_MASK_BRANCH %bb.6, implicit $exec
|
|
S_BRANCH %bb.4
|
|
|
|
bb.4:
|
|
successors: %bb.5(0x04000000), %bb.4(0x7c000000)
|
|
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_NOP 0
|
|
S_CBRANCH_EXECZ %bb.4, implicit $exec
|
|
|
|
bb.5:
|
|
successors: %bb.6(0x80000000)
|
|
|
|
bb.6:
|
|
successors: %bb.7(0x04000000), %bb.1(0x7c000000)
|
|
|
|
S_CBRANCH_VCCZ %bb.1, implicit $vcc
|
|
|
|
bb.7:
|
|
S_ENDPGM 0
|
|
...
|