c10921fa1a
D125887 changed the ctlz/cttz despeculation transform to insert
a freeze for the introduced branch on zero. While this does fix
the "branch on poison" issue, we may still get in trouble if we
pick a different value for the branch and for the ctz argument
(i.e. non-zero for the branch, but zero for the ctz). To avoid
this, we should use the same frozen value in both positions.
This does cause a regression in RISCV codegen by introducing an
additional sext. The DAG looks like this:
t0: ch = EntryToken
t2: i64,ch = CopyFromReg t0, Register:i64 %3
t4: i64 = AssertSext t2, ValueType:ch:i32
t23: i64 = freeze t4
t9: ch = CopyToReg t0, Register:i64 %0, t23
t16: ch = CopyToReg t0, Register:i64 %4, Constant:i64<32>
t18: ch = TokenFactor t9, t16
t25: i64 = sign_extend_inreg t23, ValueType:ch:i32
t24: i64 = setcc t25, Constant:i64<0>, seteq:ch
t28: i64 = and t24, Constant:i64<1>
t19: ch = brcond t18, t28, BasicBlock:ch<cond.end 0x8311f68>
t21: ch = br t19, BasicBlock:ch<cond.false 0x8311e80>
I don't see a really obvious way to improve this, as we can't push
the freeze past the AssertSext (which may produce poison).
Differential Revision: https://reviews.llvm.org/D126638
86 lines
3.3 KiB
LLVM
86 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -codegenprepare < %s | FileCheck %s --check-prefix=SLOW
|
|
; RUN: opt -S -codegenprepare -mattr=+bmi < %s | FileCheck %s --check-prefix=FAST_TZ
|
|
; RUN: opt -S -codegenprepare -mattr=+lzcnt < %s | FileCheck %s --check-prefix=FAST_LZ
|
|
|
|
target triple = "x86_64-unknown-unknown"
|
|
target datalayout = "e-n32:64"
|
|
|
|
; If the intrinsic is cheap, nothing should change.
|
|
; If the intrinsic is expensive, check if the input is zero to avoid the call.
|
|
; This is undoing speculation that may have been created by SimplifyCFG + InstCombine.
|
|
|
|
define i64 @cttz(i64 %A) {
|
|
; SLOW-LABEL: @cttz(
|
|
; SLOW-NEXT: entry:
|
|
; SLOW-NEXT: [[A_FR:%.*]] = freeze i64 [[A:%.*]]
|
|
; SLOW-NEXT: [[CMPZ:%.*]] = icmp eq i64 [[A_FR]], 0
|
|
; SLOW-NEXT: br i1 [[CMPZ]], label [[COND_END:%.*]], label [[COND_FALSE:%.*]]
|
|
; SLOW: cond.false:
|
|
; SLOW-NEXT: [[Z:%.*]] = call i64 @llvm.cttz.i64(i64 [[A_FR]], i1 true)
|
|
; SLOW-NEXT: br label [[COND_END]]
|
|
; SLOW: cond.end:
|
|
; SLOW-NEXT: [[CTZ:%.*]] = phi i64 [ 64, [[ENTRY:%.*]] ], [ [[Z]], [[COND_FALSE]] ]
|
|
; SLOW-NEXT: ret i64 [[CTZ]]
|
|
;
|
|
; FAST_TZ-LABEL: @cttz(
|
|
; FAST_TZ-NEXT: entry:
|
|
; FAST_TZ-NEXT: [[Z:%.*]] = call i64 @llvm.cttz.i64(i64 [[A:%.*]], i1 false)
|
|
; FAST_TZ-NEXT: ret i64 [[Z]]
|
|
;
|
|
; FAST_LZ-LABEL: @cttz(
|
|
; FAST_LZ-NEXT: entry:
|
|
; FAST_LZ-NEXT: [[A_FR:%.*]] = freeze i64 [[A:%.*]]
|
|
; FAST_LZ-NEXT: [[CMPZ:%.*]] = icmp eq i64 [[A_FR]], 0
|
|
; FAST_LZ-NEXT: br i1 [[CMPZ]], label [[COND_END:%.*]], label [[COND_FALSE:%.*]]
|
|
; FAST_LZ: cond.false:
|
|
; FAST_LZ-NEXT: [[Z:%.*]] = call i64 @llvm.cttz.i64(i64 [[A_FR]], i1 true)
|
|
; FAST_LZ-NEXT: br label [[COND_END]]
|
|
; FAST_LZ: cond.end:
|
|
; FAST_LZ-NEXT: [[CTZ:%.*]] = phi i64 [ 64, [[ENTRY:%.*]] ], [ [[Z]], [[COND_FALSE]] ]
|
|
; FAST_LZ-NEXT: ret i64 [[CTZ]]
|
|
;
|
|
entry:
|
|
%z = call i64 @llvm.cttz.i64(i64 %A, i1 false)
|
|
ret i64 %z
|
|
}
|
|
|
|
define i64 @ctlz(i64 %A) {
|
|
; SLOW-LABEL: @ctlz(
|
|
; SLOW-NEXT: entry:
|
|
; SLOW-NEXT: [[A_FR:%.*]] = freeze i64 [[A:%.*]]
|
|
; SLOW-NEXT: [[CMPZ:%.*]] = icmp eq i64 [[A_FR]], 0
|
|
; SLOW-NEXT: br i1 [[CMPZ]], label [[COND_END:%.*]], label [[COND_FALSE:%.*]]
|
|
; SLOW: cond.false:
|
|
; SLOW-NEXT: [[Z:%.*]] = call i64 @llvm.ctlz.i64(i64 [[A_FR]], i1 true)
|
|
; SLOW-NEXT: br label [[COND_END]]
|
|
; SLOW: cond.end:
|
|
; SLOW-NEXT: [[CTZ:%.*]] = phi i64 [ 64, [[ENTRY:%.*]] ], [ [[Z]], [[COND_FALSE]] ]
|
|
; SLOW-NEXT: ret i64 [[CTZ]]
|
|
;
|
|
; FAST_TZ-LABEL: @ctlz(
|
|
; FAST_TZ-NEXT: entry:
|
|
; FAST_TZ-NEXT: [[A_FR:%.*]] = freeze i64 [[A:%.*]]
|
|
; FAST_TZ-NEXT: [[CMPZ:%.*]] = icmp eq i64 [[A_FR]], 0
|
|
; FAST_TZ-NEXT: br i1 [[CMPZ]], label [[COND_END:%.*]], label [[COND_FALSE:%.*]]
|
|
; FAST_TZ: cond.false:
|
|
; FAST_TZ-NEXT: [[Z:%.*]] = call i64 @llvm.ctlz.i64(i64 [[A_FR]], i1 true)
|
|
; FAST_TZ-NEXT: br label [[COND_END]]
|
|
; FAST_TZ: cond.end:
|
|
; FAST_TZ-NEXT: [[CTZ:%.*]] = phi i64 [ 64, [[ENTRY:%.*]] ], [ [[Z]], [[COND_FALSE]] ]
|
|
; FAST_TZ-NEXT: ret i64 [[CTZ]]
|
|
;
|
|
; FAST_LZ-LABEL: @ctlz(
|
|
; FAST_LZ-NEXT: entry:
|
|
; FAST_LZ-NEXT: [[Z:%.*]] = call i64 @llvm.ctlz.i64(i64 [[A:%.*]], i1 false)
|
|
; FAST_LZ-NEXT: ret i64 [[Z]]
|
|
;
|
|
entry:
|
|
%z = call i64 @llvm.ctlz.i64(i64 %A, i1 false)
|
|
ret i64 %z
|
|
}
|
|
|
|
declare i64 @llvm.cttz.i64(i64, i1)
|
|
declare i64 @llvm.ctlz.i64(i64, i1)
|
|
|