bfb9b8e075
We call tail-call-elim near the beginning of the pipeline, but that is too early to annotate calls that get added later. In the motivating case from issue #47852, the missing 'tail' on memset leads to sub-optimal codegen. I experimented with removing the early instance of tail-call-elim instead of just adding another pass, but that appears to be slightly worse for compile-time: +0.15% vs. +0.08% time. "tailcall" shows adding the pass; "tailcall2" shows moving the pass to later, then adding the original early pass back (so 1596886802 is functionally equivalent to 180b0439dc ): https://llvm-compile-time-tracker.com/index.php?config=NewPM-O3&stat=instructions&remote=rotateright Note that there was an effort to split the tail call functionality into 2 passes - that could help reduce compile-time if we find that this change costs more in compile-time than expected based on the preliminary testing: D60031 Differential Revision: https://reviews.llvm.org/D130374
92 lines
2.5 KiB
LLVM
92 lines
2.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -S -O1 | FileCheck %s
|
|
; RUN: opt -passes='default<O1>' -S < %s | FileCheck %s
|
|
|
|
; In all tests, expect instcombine to canonicalize the select patterns
|
|
; for min/max/abs to allow CSE and subsequent simplification.
|
|
|
|
; TODO:
|
|
; This should be reduced to 0, but we are missing some
|
|
; fold(s) in instcombine.
|
|
|
|
define i8 @smax_nsw(i8 %a, i8 %b) {
|
|
; CHECK-LABEL: @smax_nsw(
|
|
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i8 [[A:%.*]], [[B:%.*]]
|
|
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i8 [[A]], [[B]]
|
|
; CHECK-NEXT: [[M1:%.*]] = select i1 [[CMP1]], i8 0, i8 [[SUB]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = tail call i8 @llvm.smax.i8(i8 [[SUB]], i8 0)
|
|
; CHECK-NEXT: [[R:%.*]] = sub i8 [[TMP1]], [[M1]]
|
|
; CHECK-NEXT: ret i8 [[R]]
|
|
;
|
|
%sub = sub nsw i8 %a, %b
|
|
%cmp1 = icmp slt i8 %a, %b
|
|
%cmp2 = icmp sgt i8 %sub, 0
|
|
%m1 = select i1 %cmp1, i8 0, i8 %sub
|
|
%m2 = select i1 %cmp2, i8 %sub, i8 0
|
|
%r = sub i8 %m2, %m1
|
|
ret i8 %r
|
|
}
|
|
|
|
; or (abs a), (abs a) --> abs a
|
|
|
|
define i8 @abs_swapped(i8 %a) {
|
|
; CHECK-LABEL: @abs_swapped(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = tail call i8 @llvm.abs.i8(i8 [[A:%.*]], i1 false)
|
|
; CHECK-NEXT: ret i8 [[TMP1]]
|
|
;
|
|
%neg = sub i8 0, %a
|
|
%cmp1 = icmp sgt i8 %a, 0
|
|
%cmp2 = icmp slt i8 %a, 0
|
|
%m1 = select i1 %cmp1, i8 %a, i8 %neg
|
|
%m2 = select i1 %cmp2, i8 %neg, i8 %a
|
|
%r = or i8 %m2, %m1
|
|
ret i8 %r
|
|
}
|
|
|
|
; xor (nabs a), (nabs a) --> 0
|
|
|
|
define i8 @nabs_swapped(i8 %a) {
|
|
; CHECK-LABEL: @nabs_swapped(
|
|
; CHECK-NEXT: ret i8 0
|
|
;
|
|
%neg = sub i8 0, %a
|
|
%cmp1 = icmp slt i8 %a, 0
|
|
%cmp2 = icmp sgt i8 %a, 0
|
|
%m1 = select i1 %cmp1, i8 %a, i8 %neg
|
|
%m2 = select i1 %cmp2, i8 %neg, i8 %a
|
|
%r = xor i8 %m2, %m1
|
|
ret i8 %r
|
|
}
|
|
|
|
; xor (abs a), (abs a) --> 0
|
|
|
|
define i8 @abs_different_constants(i8 %a) {
|
|
; CHECK-LABEL: @abs_different_constants(
|
|
; CHECK-NEXT: ret i8 0
|
|
;
|
|
%neg = sub i8 0, %a
|
|
%cmp1 = icmp sgt i8 %a, -1
|
|
%cmp2 = icmp slt i8 %a, 0
|
|
%m1 = select i1 %cmp1, i8 %a, i8 %neg
|
|
%m2 = select i1 %cmp2, i8 %neg, i8 %a
|
|
%r = xor i8 %m2, %m1
|
|
ret i8 %r
|
|
}
|
|
|
|
; or (nabs a), (nabs a) --> nabs a
|
|
|
|
define i8 @nabs_different_constants(i8 %a) {
|
|
; CHECK-LABEL: @nabs_different_constants(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = tail call i8 @llvm.abs.i8(i8 [[A:%.*]], i1 false)
|
|
; CHECK-NEXT: [[M1:%.*]] = sub i8 0, [[TMP1]]
|
|
; CHECK-NEXT: ret i8 [[M1]]
|
|
;
|
|
%neg = sub i8 0, %a
|
|
%cmp1 = icmp slt i8 %a, 0
|
|
%cmp2 = icmp sgt i8 %a, -1
|
|
%m1 = select i1 %cmp1, i8 %a, i8 %neg
|
|
%m2 = select i1 %cmp2, i8 %neg, i8 %a
|
|
%r = or i8 %m2, %m1
|
|
ret i8 %r
|
|
}
|