[MachineOutliner] AArch64: Avoid saving + restoring LR if possible
This commit allows the outliner to avoid saving and restoring the link register
on AArch64 when it is dead within an entire class of candidates.
This introduces changes to the way the outliner interfaces with the target.
For example, the target now interfaces with the outliner using a
MachineOutlinerInfo struct rather than by using getOutliningCallOverhead and
getOutliningFrameOverhead.
This also improves several comments on the outliner's cost model.
https://reviews.llvm.org/D36721
llvm-svn: 314341
diff --git a/llvm/test/CodeGen/AArch64/machine-outliner-remarks.ll b/llvm/test/CodeGen/AArch64/machine-outliner-remarks.ll
index 113f343..7f3a4f4 100644
--- a/llvm/test/CodeGen/AArch64/machine-outliner-remarks.ll
+++ b/llvm/test/CodeGen/AArch64/machine-outliner-remarks.ll
@@ -1,7 +1,7 @@
; RUN: llc %s -enable-machine-outliner -mtriple=aarch64-unknown-unknown -pass-remarks-missed=machine-outliner -o /dev/null 2>&1 | FileCheck %s
; CHECK: machine-outliner-remarks.ll:5:9:
; CHECK-SAME: Did not outline 2 instructions from 2 locations.
-; CHECK-SAME: Instructions from outlining all occurrences (9) >=
+; CHECK-SAME: Instructions from outlining all occurrences (7) >=
; CHECK-SAME: Unoutlined instruction count (4)
; CHECK-SAME: (Also found at: machine-outliner-remarks.ll:13:9)
; RUN: llc %s -enable-machine-outliner -mtriple=aarch64-unknown-unknown -o /dev/null -pass-remarks-missed=machine-outliner -pass-remarks-output=%t.yaml
@@ -19,7 +19,7 @@
; YAML-NEXT: - NumOccurrences: '2'
; YAML-NEXT: - String: ' locations.'
; YAML-NEXT: - String: ' Instructions from outlining all occurrences ('
-; YAML-NEXT: - OutliningCost: '9'
+; YAML-NEXT: - OutliningCost: '7'
; YAML-NEXT: - String: ')'
; YAML-NEXT: - String: ' >= Unoutlined instruction count ('
; YAML-NEXT: - NotOutliningCost: '4'
diff --git a/llvm/test/CodeGen/AArch64/machine-outliner.mir b/llvm/test/CodeGen/AArch64/machine-outliner.mir
index 822ceb2..3ff2d2a 100644
--- a/llvm/test/CodeGen/AArch64/machine-outliner.mir
+++ b/llvm/test/CodeGen/AArch64/machine-outliner.mir
@@ -1,42 +1,38 @@
# RUN: llc -mtriple=aarch64--- -run-pass=machine-outliner %s -o - | FileCheck %s
--- |
- target triple = "aarch64---"
-
+
define i32 @main() #0 {
- entry:
ret i32 0
}
- attributes #0 = { noinline noredzone nounwind optnone ssp uwtable }
-
-# CHECK-LABEL: @OUTLINED_FUNCTION_0
-
+ define void @bar(i32 %a) #0 {
+ ret void
+ }
+
+ attributes #0 = { noinline noredzone "no-frame-pointer-elim"="true" }
...
---
# This test ensures that we
# - Create outlined functions
# - Don't outline anything to do with LR or W30
+# - Save LR when it's not available
#
# CHECK-LABEL: name: main
-# CHECK: BL @OUTLINED_FUNCTION_0
-# CHECK: STRHHroW %w16, %x9, %w30, 1, 1
-# CHECK: %lr = ORRXri %xzr, 1
-# CHECK: BL @OUTLINED_FUNCTION_0
-# CHECK: STRHHroW %w16, %x9, %w30, 1, 1
-# CHECK: %lr = ORRXri %xzr, 1
-# CHECK: BL @OUTLINED_FUNCTION_0
-# CHECK: STRHHroW %w16, %x9, %w30, 1, 1
-# CHECK: %lr = ORRXri %xzr, 1
+# CHECK: BL @OUTLINED_FUNCTION_[[F0:[0-9]+]]
+# CHECK-NEXT: early-clobber %sp, %lr = LDRXpost %sp, 16
+# CHECK-NEXT: STRHHroW %w16, %x9, %w30, 1, 1
+# CHECK-NEXT: %lr = ORRXri %xzr, 1
+# CHECK: BL @OUTLINED_FUNCTION_[[F0]]
+# CHECK-NEXT: early-clobber %sp, %lr = LDRXpost %sp, 16
+# CHECK-NEXT: STRHHroW %w16, %x9, %w30, 1, 1
+# CHECK-NEXT: %lr = ORRXri %xzr, 1
+# CHECK: BL @OUTLINED_FUNCTION_[[F0]]
+# CHECK-NEXT: early-clobber %sp, %lr = LDRXpost %sp, 16
+# CHECK-NEXT: STRHHroW %w16, %x9, %w30, 1, 1
+# CHECK-NEXT: %lr = ORRXri %xzr, 1
name: main
-alignment: 2
-tracksRegLiveness: true
-frameInfo:
- stackSize: 16
- maxAlignment: 4
- maxCallFrameSize: 0
-
body: |
- bb.0.entry:
+ bb.0:
%sp = frame-setup SUBXri %sp, 16, 0
%x9 = ORRXri %xzr, 1
%w16 = ORRWri %wzr, 1
@@ -74,8 +70,43 @@
STRHHroW %w16, %x9, %w30, 1, 1
%lr = ORRXri %xzr, 1
- %w5 = ORRWri %wzr, 1995
-
%sp = ADDXri %sp, 16, 0
RET undef %lr
-
\ No newline at end of file
+
+...
+---
+# This test ensures that we can avoid saving LR when it's available.
+# CHECK-LABEL: bb.1:
+# CHECK: BL @OUTLINED_FUNCTION_[[F1:[0-9]+]], implicit-def %lr, implicit %sp
+# CHECK-NEXT: %w17 = ORRWri %wzr, 2
+# CHECK-NEXT: BL @OUTLINED_FUNCTION_[[F1]], implicit-def %lr, implicit %sp
+# CHECK-NEXT: %w8 = ORRWri %wzr, 0
+name: bar
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: %w0, %lr, %w8
+ %sp = frame-setup SUBXri %sp, 32, 0
+ %fp = frame-setup ADDXri %sp, 16, 0
+
+ bb.1:
+ %w17 = ORRWri %wzr, 1
+ %w17 = ORRWri %wzr, 1
+ %w17 = ORRWri %wzr, 1
+ %w17 = ORRWri %wzr, 1
+ %w17 = ORRWri %wzr, 2
+ %w17 = ORRWri %wzr, 1
+ %w17 = ORRWri %wzr, 1
+ %w17 = ORRWri %wzr, 1
+ %w17 = ORRWri %wzr, 1
+ %w8 = ORRWri %wzr, 0
+
+ bb.2:
+ %fp, %lr = LDPXi %sp, 2
+ %sp = ADDXri %sp, 32, 0
+ RET undef %lr
+
+...
+
+# CHECK-LABEL: name: OUTLINED_FUNCTION_{{[0-9]}}
+# CHECK=LABEL: name: OUTLINED_FUNCTION_{{[1-9]}}
diff --git a/llvm/test/CodeGen/X86/machine-outliner.ll b/llvm/test/CodeGen/X86/machine-outliner.ll
index b4a277e..29cf32f 100644
--- a/llvm/test/CodeGen/X86/machine-outliner.ll
+++ b/llvm/test/CodeGen/X86/machine-outliner.ll
@@ -96,14 +96,14 @@
attributes #0 = { noredzone nounwind ssp uwtable "no-frame-pointer-elim"="true" }
-; CHECK-LABEL: l_OUTLINED_FUNCTION_1:
+; CHECK-LABEL: l_OUTLINED_FUNCTION_{{[0-9]+}}:
; CHECK: movl $1, -{{[0-9]+}}(%rbp)
; CHECK-NEXT: movl $2, -{{[0-9]+}}(%rbp)
; CHECK-NEXT: movl $3, -{{[0-9]+}}(%rbp)
; CHECK-NEXT: movl $4, -{{[0-9]+}}(%rbp)
; CHECK-NEXT: retq
-; CHECK-LABEL: l_OUTLINED_FUNCTION_0:
+; CHECK-LABEL: l_OUTLINED_FUNCTION_{{[0-9]+}}:
; CHECK: movl $1, -{{[0-9]+}}(%rbp)
; CHECK-NEXT: movl $2, -{{[0-9]+}}(%rbp)
; CHECK-NEXT: movl $3, -{{[0-9]+}}(%rbp)