maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AArch64/fast-isel-tbz.ll

312 lines
6.5 KiB
LLVM
Raw Normal View History

[AArch64] Register passes so they can be run by llc Initialize all AArch64-specific passes in the TargetMachine so they can be run by llc. This can lead to conflicts in opt with some command line options that share the same name as the pass, so I took this opportunity to do some cleanups: * rename all relevant command line options from "aarch64-blah" to "aarch64-enable-blah" and update the tests accordingly * run clang-format on their declarations * move all these declarations to a common place (the TargetMachine) as opposed to having them scattered around (AArch64BranchRelaxation and AArch64AddressTypePromotion were the only offenders) llvm-svn: 277322
2016-08-01 13:56:57 +08:00
; RUN: llc -disable-peephole -aarch64-enable-atomic-cfg-tidy=0 -verify-machineinstrs -mtriple=aarch64-apple-darwin < %s | FileCheck %s
; RUN: llc -disable-peephole -fast-isel -fast-isel-abort=1 -aarch64-enable-atomic-cfg-tidy=0 -verify-machineinstrs -mtriple=aarch64-apple-darwin < %s | FileCheck --check-prefix=CHECK --check-prefix=FAST %s
Recommit r218010 [FastISel][AArch64] Fold bit test and branch into TBZ and TBNZ. Note: This version fixed an issue with the TBZ/TBNZ instructions that were generated in FastISel. The issue was that the 64bit version of TBZ (TBZX) automagically sets the upper bit of the immediate field that is used to specify the bit we want to test. To test for any of the lower 32bits we have to first extract the subregister and use the 32bit version of the TBZ instruction (TBZW). Original commit message: Teach selectBranch to fold bit test and branch into a single instruction (TBZ or TBNZ). llvm-svn: 218693
2014-10-01 03:59:35 +08:00
define i32 @icmp_eq_i8(i8 zeroext %a) {
; CHECK-LABEL: icmp_eq_i8
; CHECK: tbz {{w[0-9]+}}, #0, {{LBB.+_2}}
%1 = and i8 %a, 1
%2 = icmp eq i8 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_eq_i16(i16 zeroext %a) {
; CHECK-LABEL: icmp_eq_i16
; CHECK: tbz w0, #1, {{LBB.+_2}}
%1 = and i16 %a, 2
%2 = icmp eq i16 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_eq_i32(i32 %a) {
; CHECK-LABEL: icmp_eq_i32
; CHECK: tbz w0, #2, {{LBB.+_2}}
%1 = and i32 %a, 4
%2 = icmp eq i32 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_eq_i64_1(i64 %a) {
; CHECK-LABEL: icmp_eq_i64_1
; CHECK: tbz w0, #3, {{LBB.+_2}}
%1 = and i64 %a, 8
%2 = icmp eq i64 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_eq_i64_2(i64 %a) {
; CHECK-LABEL: icmp_eq_i64_2
; CHECK: tbz x0, #32, {{LBB.+_2}}
%1 = and i64 %a, 4294967296
%2 = icmp eq i64 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_ne_i8(i8 zeroext %a) {
; CHECK-LABEL: icmp_ne_i8
; CHECK: tbnz w0, #0, {{LBB.+_2}}
%1 = and i8 %a, 1
%2 = icmp ne i8 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_ne_i16(i16 zeroext %a) {
; CHECK-LABEL: icmp_ne_i16
; CHECK: tbnz w0, #1, {{LBB.+_2}}
%1 = and i16 %a, 2
%2 = icmp ne i16 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_ne_i32(i32 %a) {
; CHECK-LABEL: icmp_ne_i32
; CHECK: tbnz w0, #2, {{LBB.+_2}}
%1 = and i32 %a, 4
%2 = icmp ne i32 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_ne_i64_1(i64 %a) {
; CHECK-LABEL: icmp_ne_i64_1
; CHECK: tbnz w0, #3, {{LBB.+_2}}
%1 = and i64 %a, 8
%2 = icmp ne i64 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_ne_i64_2(i64 %a) {
; CHECK-LABEL: icmp_ne_i64_2
; CHECK: tbnz x0, #32, {{LBB.+_2}}
%1 = and i64 %a, 4294967296
%2 = icmp ne i64 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
[FastISel][AArch64] Fix and extend the tbz/tbnz pattern matching. The pattern matching failed to recognize all instances of "-1", because when comparing against "-1" we didn't use an APInt of the same bitwidth. This commit fixes this and also adds inverse versions of the conditon to catch more cases. llvm-svn: 222722
2014-11-25 12:16:15 +08:00
define i32 @icmp_slt_i8(i8 zeroext %a) {
; FAST-LABEL: icmp_slt_i8
; FAST: tbnz w0, #7, {{LBB.+_2}}
%1 = icmp slt i8 %a, 0
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_slt_i16(i16 zeroext %a) {
; FAST-LABEL: icmp_slt_i16
; FAST: tbnz w0, #15, {{LBB.+_2}}
%1 = icmp slt i16 %a, 0
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_slt_i32(i32 %a) {
; CHECK-LABEL: icmp_slt_i32
; CHECK: tbnz w0, #31, {{LBB.+_2}}
%1 = icmp slt i32 %a, 0
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_slt_i64(i64 %a) {
; CHECK-LABEL: icmp_slt_i64
; CHECK: tbnz x0, #63, {{LBB.+_2}}
%1 = icmp slt i64 %a, 0
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sge_i8(i8 zeroext %a) {
; FAST-LABEL: icmp_sge_i8
; FAST: tbz w0, #7, {{LBB.+_2}}
%1 = icmp sge i8 %a, 0
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sge_i16(i16 zeroext %a) {
; FAST-LABEL: icmp_sge_i16
; FAST: tbz w0, #15, {{LBB.+_2}}
%1 = icmp sge i16 %a, 0
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sle_i8(i8 zeroext %a) {
; FAST-LABEL: icmp_sle_i8
; FAST: tbnz w0, #7, {{LBB.+_2}}
%1 = icmp sle i8 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sle_i16(i16 zeroext %a) {
; FAST-LABEL: icmp_sle_i16
; FAST: tbnz w0, #15, {{LBB.+_2}}
%1 = icmp sle i16 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sle_i32(i32 %a) {
; CHECK-LABEL: icmp_sle_i32
; CHECK: tbnz w0, #31, {{LBB.+_2}}
%1 = icmp sle i32 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sle_i64(i64 %a) {
; CHECK-LABEL: icmp_sle_i64
; CHECK: tbnz x0, #63, {{LBB.+_2}}
%1 = icmp sle i64 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sgt_i8(i8 zeroext %a) {
; FAST-LABEL: icmp_sgt_i8
; FAST: tbz w0, #7, {{LBB.+_2}}
%1 = icmp sgt i8 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sgt_i16(i16 zeroext %a) {
; FAST-LABEL: icmp_sgt_i16
; FAST: tbz w0, #15, {{LBB.+_2}}
%1 = icmp sgt i16 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sgt_i32(i32 %a) {
; CHECK-LABEL: icmp_sgt_i32
; CHECK: tbz w0, #31, {{LBB.+_2}}
%1 = icmp sgt i32 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
define i32 @icmp_sgt_i64(i64 %a) {
; FAST-LABEL: icmp_sgt_i64
; FAST: tbz x0, #63, {{LBB.+_2}}
%1 = icmp sgt i64 %a, -1
br i1 %1, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
[FastISel][AArch64] Don't fold the 'and' instruction into the 'tbz/tbnz' instruction if it is in a different basic block. This fixes a bug where the input register was not defined for the 'tbz/tbnz' instruction. This happened, because we folded the 'and' instruction from a different basic block. This fixes rdar://problem/18784013. llvm-svn: 220704
2014-10-28 03:16:48 +08:00
; Test that we don't fold the 'and' instruction into the compare.
define i32 @icmp_eq_and_i32(i32 %a, i1 %c) {
; CHECK-LABEL: icmp_eq_and_i32
[CodeGenPrepare] Sink and duplicate more 'and' instructions. Summary: Rework the code that was sinking/duplicating (icmp and, 0) sequences into blocks where they were being used by conditional branches to form more tbz instructions on AArch64. The new code is more general in that it just looks for 'and's that have all icmp 0's as users, with a target hook used to select which subset of 'and' instructions to consider. This change also enables 'and' sinking for X86, where it is more widely beneficial than on AArch64. The 'and' sinking/duplicating code is moved into the optimizeInst phase of CodeGenPrepare, where it can take advantage of the fact the OptimizeCmpExpression has already sunk/duplicated any icmps into the blocks where they are used. One minor complication from this change is that optimizeLoadExt needed to be updated to always mark 'and's it has determined should be in the same block as their feeding load in the InsertedInsts set to avoid an infinite loop of hoisting and sinking the same 'and'. This change fixes a regression on X86 in the tsan runtime caused by moving GVNHoist to a later place in the optimization pipeline (see PR31382). Reviewers: t.p.northover, qcolombet, MatzeB Subscribers: aemerson, mcrosier, sebpop, llvm-commits Differential Revision: https://reviews.llvm.org/D28813 llvm-svn: 295746
2017-02-22 02:53:14 +08:00
; CHECK: and [[REG:w[0-9]+]], w0, #0x3
[FastISel][AArch64] Don't fold the 'and' instruction into the 'tbz/tbnz' instruction if it is in a different basic block. This fixes a bug where the input register was not defined for the 'tbz/tbnz' instruction. This happened, because we folded the 'and' instruction from a different basic block. This fixes rdar://problem/18784013. llvm-svn: 220704
2014-10-28 03:16:48 +08:00
; CHECK-NEXT: cbz [[REG]], {{LBB.+_3}}
[CodeGenPrepare] Sink and duplicate more 'and' instructions. Summary: Rework the code that was sinking/duplicating (icmp and, 0) sequences into blocks where they were being used by conditional branches to form more tbz instructions on AArch64. The new code is more general in that it just looks for 'and's that have all icmp 0's as users, with a target hook used to select which subset of 'and' instructions to consider. This change also enables 'and' sinking for X86, where it is more widely beneficial than on AArch64. The 'and' sinking/duplicating code is moved into the optimizeInst phase of CodeGenPrepare, where it can take advantage of the fact the OptimizeCmpExpression has already sunk/duplicated any icmps into the blocks where they are used. One minor complication from this change is that optimizeLoadExt needed to be updated to always mark 'and's it has determined should be in the same block as their feeding load in the InsertedInsts set to avoid an infinite loop of hoisting and sinking the same 'and'. This change fixes a regression on X86 in the tsan runtime caused by moving GVNHoist to a later place in the optimization pipeline (see PR31382). Reviewers: t.p.northover, qcolombet, MatzeB Subscribers: aemerson, mcrosier, sebpop, llvm-commits Differential Revision: https://reviews.llvm.org/D28813 llvm-svn: 295746
2017-02-22 02:53:14 +08:00
%1 = and i32 %a, 3
br i1 %c, label %bb0, label %bb2
bb0:
%2 = icmp eq i32 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
; Test that we do fold the 'and' instruction into the compare and
; generate a tbz instruction for the conditional branch.
define i32 @icmp_eq_and1bit_i32(i32 %a, i1 %c) {
; CHECK-LABEL: icmp_eq_and1bit_i32
; CHECK: tbz {{w[0-9]+}}, #2, {{LBB.+_3}}
[FastISel][AArch64] Don't fold the 'and' instruction into the 'tbz/tbnz' instruction if it is in a different basic block. This fixes a bug where the input register was not defined for the 'tbz/tbnz' instruction. This happened, because we folded the 'and' instruction from a different basic block. This fixes rdar://problem/18784013. llvm-svn: 220704
2014-10-28 03:16:48 +08:00
%1 = and i32 %a, 4
br i1 %c, label %bb0, label %bb2
bb0:
%2 = icmp eq i32 %1, 0
br i1 %2, label %bb1, label %bb2, !prof !0
bb1:
ret i32 1
bb2:
ret i32 0
}
IR: Make metadata typeless in assembly Now that `Metadata` is typeless, reflect that in the assembly. These are the matching assembly changes for the metadata/value split in r223802. - Only use the `metadata` type when referencing metadata from a call intrinsic -- i.e., only when it's used as a `Value`. - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode` when referencing it from call intrinsics. So, assembly like this: define @foo(i32 %v) { call void @llvm.foo(metadata !{i32 %v}, metadata !0) call void @llvm.foo(metadata !{i32 7}, metadata !0) call void @llvm.foo(metadata !1, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{metadata !3}, metadata !0) ret void, !bar !2 } !0 = metadata !{metadata !2} !1 = metadata !{i32* @global} !2 = metadata !{metadata !3} !3 = metadata !{} turns into this: define @foo(i32 %v) { call void @llvm.foo(metadata i32 %v, metadata !0) call void @llvm.foo(metadata i32 7, metadata !0) call void @llvm.foo(metadata i32* @global, metadata !0) call void @llvm.foo(metadata !3, metadata !0) call void @llvm.foo(metadata !{!3}, metadata !0) ret void, !bar !2 } !0 = !{!2} !1 = !{i32* @global} !2 = !{!3} !3 = !{} I wrote an upgrade script that handled almost all of the tests in llvm and many of the tests in cfe (even handling many `CHECK` lines). I've attached it (or will attach it in a moment if you're speedy) to PR21532 to help everyone update their out-of-tree testcases. This is part of PR21532. llvm-svn: 224257
2014-12-16 03:07:53 +08:00
!0 = !{!"branch_weights", i32 0, i32 2147483647}
!1 = !{!"branch_weights", i32 2147483647, i32 0}