llvm-6502/test/CodeGen/PowerPC/sjlj.ll
Hal Finkel 411dea0e72 PPC: Enable aggressive anti-dependency breaking
Aggressive anti-dependency breaking is enabled by default for all PPC cores.
This provides a general speedup on the P7 and other platforms (among other
factors, the instruction group formation for the non-embedded PPC cores is done
during post-RA scheduling). In order to do this safely, the incompatibility
between uses of the MFOCRF instruction and anti-dependency breaking are
resolved by marking MFOCRF with hasExtraSrcRegAllocReq. As noted in the removed
FIXME, the problem was that MFOCRF's output is sensitive to the identify of the
source register, and always paired with a shift to undo this effect. Because
anti-dependency breaking is unaware of this hidden dependency of the shift
amount on the source register of the MFOCRF instruction, changing that register
must be inhibited.

Two test cases were adjusted: The SjLj test was made more insensitive to
register choices and scheduling; the saveCR test disabled anti-dependency
breaking because part of what it is testing is proper register reuse.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190587 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-12 05:24:49 +00:00

161 lines
4.9 KiB
LLVM

; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 | FileCheck %s
; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 | FileCheck -check-prefix=CHECK-NOAV %s
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
%struct.__jmp_buf_tag = type { [64 x i64], i32, %struct.__sigset_t, [8 x i8] }
%struct.__sigset_t = type { [16 x i64] }
@env_sigill = internal global [1 x %struct.__jmp_buf_tag] zeroinitializer, align 16
define void @foo() #0 {
entry:
call void @llvm.eh.sjlj.longjmp(i8* bitcast ([1 x %struct.__jmp_buf_tag]* @env_sigill to i8*))
unreachable
; CHECK: @foo
; CHECK: addis [[REG:[0-9]+]], 2, env_sigill@toc@ha
; CHECK: addi [[REG]], [[REG]], env_sigill@toc@l
; CHECK: ld 31, 0([[REG]])
; CHECK: ld [[REG2:[0-9]+]], 8([[REG]])
; CHECK: ld 1, 16([[REG]])
; CHECK: mtctr [[REG2]]
; CHECK: ld 30, 32([[REG]])
; CHECK: ld 2, 24([[REG]])
; CHECK: bctr
return: ; No predecessors!
ret void
}
declare void @llvm.eh.sjlj.longjmp(i8*) #1
define signext i32 @main() #0 {
entry:
%retval = alloca i32, align 4
store i32 0, i32* %retval
%0 = call i8* @llvm.frameaddress(i32 0)
store i8* %0, i8** bitcast ([1 x %struct.__jmp_buf_tag]* @env_sigill to i8**)
%1 = call i8* @llvm.stacksave()
store i8* %1, i8** getelementptr (i8** bitcast ([1 x %struct.__jmp_buf_tag]* @env_sigill to i8**), i32 2)
%2 = call i32 @llvm.eh.sjlj.setjmp(i8* bitcast ([1 x %struct.__jmp_buf_tag]* @env_sigill to i8*))
%tobool = icmp ne i32 %2, 0
br i1 %tobool, label %if.then, label %if.else
if.then: ; preds = %entry
store i32 1, i32* %retval
br label %return
if.else: ; preds = %entry
call void @foo()
br label %if.end
if.end: ; preds = %if.else
store i32 0, i32* %retval
br label %return
return: ; preds = %if.end, %if.then
%3 = load i32* %retval
ret i32 %3
; FIXME: We should be saving VRSAVE on Darwin, but we're not!
; CHECK: @main
; CHECK: std
; Make sure that we're not saving VRSAVE on non-Darwin:
; CHECK-NOT: mfspr
; CHECK-DAG: stfd
; CHECK-DAG: stvx
; CHECK-DAG: addis [[REG:[0-9]+]], 2, env_sigill@toc@ha
; CHECK-DAG: std 31, env_sigill@toc@l([[REG]])
; CHECK-DAG: addi [[REGA:[0-9]+]], [[REG]], env_sigill@toc@l
; CHECK-DAG: std [[REGA]], [[OFF:[0-9]+]](31) # 8-byte Folded Spill
; CHECK-DAG: std 1, 16([[REGA]])
; CHECK-DAG: std 2, 24([[REGA]])
; CHECK: bcl 20, 31, .LBB1_1
; CHECK: li 3, 1
; CHECK: #EH_SjLj_Setup .LBB1_1
; CHECK: b .LBB1_2
; CHECK: .LBB1_1:
; CHECK: mflr [[REGL:[0-9]+]]
; CHECK: ld [[REG2:[0-9]+]], [[OFF]](31) # 8-byte Folded Reload
; CHECK: std [[REGL]], 8([[REG2]])
; CHECK: li 3, 0
; CHECK: .LBB1_2:
; CHECK: lfd
; CHECK: lvx
; CHECK: ld
; CHECK: blr
; CHECK-NOAV: @main
; CHECK-NOAV-NOT: stvx
; CHECK-NOAV: bcl
; CHECK-NOAV: mflr
; CHECK-NOAV: bl foo
; CHECK-NOAV-NOT: lvx
; CHECK-NOAV: blr
}
define signext i32 @main2() #0 {
entry:
%a = alloca i8, align 64
call void @bar(i8* %a)
%retval = alloca i32, align 4
store i32 0, i32* %retval
%0 = call i8* @llvm.frameaddress(i32 0)
store i8* %0, i8** bitcast ([1 x %struct.__jmp_buf_tag]* @env_sigill to i8**)
%1 = call i8* @llvm.stacksave()
store i8* %1, i8** getelementptr (i8** bitcast ([1 x %struct.__jmp_buf_tag]* @env_sigill to i8**), i32 2)
%2 = call i32 @llvm.eh.sjlj.setjmp(i8* bitcast ([1 x %struct.__jmp_buf_tag]* @env_sigill to i8*))
%tobool = icmp ne i32 %2, 0
br i1 %tobool, label %if.then, label %if.else
if.then: ; preds = %entry
store i32 1, i32* %retval
br label %return
if.else: ; preds = %entry
call void @foo()
br label %if.end
if.end: ; preds = %if.else
store i32 0, i32* %retval
br label %return
return: ; preds = %if.end, %if.then
%3 = load i32* %retval
ret i32 %3
; CHECK: @main2
; CHECK: addis [[REG:[0-9]+]], 2, env_sigill@toc@ha
; CHECK: std 31, env_sigill@toc@l([[REG]])
; CHECK: addi [[REGB:[0-9]+]], [[REG]], env_sigill@toc@l
; CHECK-DAG: std [[REGB]], [[OFF:[0-9]+]](31) # 8-byte Folded Spill
; CHECK-DAG: std 1, 16([[REGB]])
; CHECK-DAG: std 2, 24([[REGB]])
; CHECK-DAG: std 30, 32([[REGB]])
; CHECK: bcl 20, 31,
; CHECK: blr
}
declare void @bar(i8*) #3
declare i8* @llvm.frameaddress(i32) #2
declare i8* @llvm.stacksave() #3
declare i32 @llvm.eh.sjlj.setjmp(i8*) #3
attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { noreturn nounwind }
attributes #2 = { nounwind readnone }
attributes #3 = { nounwind }