mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 11:42:57 +01:00
f61800be05
No changes relative to last time, but after a mitigation for
an AMDGPU regression landed.
---
If SimplifyInstruction() does not succeed in simplifying the
instruction, it will compute the known bits of the instruction
in the hope that all bits are known and the instruction can be
folded to a constant. I have removed a similar optimization
from InstCombine in D75801, and would like to drop this one as well.
On average, we spend ~1% of total compile-time performing this
known bits calculation. However, if we introduce some additional
statistics for known bits computations and how many of them succeed
in simplifying the instruction we get (on test-suite):
instsimplify.NumKnownBits: 216
instsimplify.NumKnownBitsComputed: 13828375
valuetracking.NumKnownBitsComputed: 45860806
Out of ~14M known bits calculations (accounting for approximately
one third of all known bits calculations), only 0.0015% succeed in
producing a constant. Those cases where we do succeed to compute
all known bits will get folded by other passes like InstCombine
later. On test-suite, only lencod.test and GCC-C-execute-pr44858.test
show a hash difference after this change. On lencod we see an
improvement (a loop phi is optimized away), on the GCC torture
test a regression (a function return value is determined only
after IPSCCP, preventing propagation from a noinline function.)
There are various regressions in InstSimplify tests. However, all
of these cases are already handled by InstCombine, and corresponding
tests have already been added there.
Differential Revision: https://reviews.llvm.org/D79294
90 lines
2.6 KiB
LLVM
90 lines
2.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -instsimplify -S < %s | FileCheck %s
|
|
|
|
define i1 @test(i8 %p, i8* %pq) {
|
|
; CHECK-LABEL: @test(
|
|
; CHECK-NEXT: ret i1 false
|
|
;
|
|
%q = load i8, i8* %pq, !range !0 ; %q is known nonzero; no known bits
|
|
%1 = or i8 %p, 2 ; %1[1] = 1
|
|
%2 = and i8 %1, 254 ; %2[0] = 0, %2[1] = 1
|
|
%A = lshr i8 %2, 1 ; We should know that %A is nonzero.
|
|
%x = icmp eq i8 %A, 0
|
|
ret i1 %x
|
|
}
|
|
|
|
!0 = !{ i8 1, i8 5 }
|
|
|
|
; The following cases only get folded by InstCombine,
|
|
; see InstCombine/shift-shift.ll. If we wanted to,
|
|
; we could explicitly handle them in InstSimplify as well.
|
|
|
|
define i32 @shl_shl(i32 %A) {
|
|
; CHECK-LABEL: @shl_shl(
|
|
; CHECK-NEXT: [[B:%.*]] = shl i32 [[A:%.*]], 6
|
|
; CHECK-NEXT: [[C:%.*]] = shl i32 [[B]], 28
|
|
; CHECK-NEXT: ret i32 [[C]]
|
|
;
|
|
%B = shl i32 %A, 6
|
|
%C = shl i32 %B, 28
|
|
ret i32 %C
|
|
}
|
|
|
|
define <2 x i33> @shl_shl_splat_vec(<2 x i33> %A) {
|
|
; CHECK-LABEL: @shl_shl_splat_vec(
|
|
; CHECK-NEXT: [[B:%.*]] = shl <2 x i33> [[A:%.*]], <i33 5, i33 5>
|
|
; CHECK-NEXT: [[C:%.*]] = shl <2 x i33> [[B]], <i33 28, i33 28>
|
|
; CHECK-NEXT: ret <2 x i33> [[C]]
|
|
;
|
|
%B = shl <2 x i33> %A, <i33 5, i33 5>
|
|
%C = shl <2 x i33> %B, <i33 28, i33 28>
|
|
ret <2 x i33> %C
|
|
}
|
|
|
|
; FIXME
|
|
|
|
define <2 x i33> @shl_shl_vec(<2 x i33> %A) {
|
|
; CHECK-LABEL: @shl_shl_vec(
|
|
; CHECK-NEXT: [[B:%.*]] = shl <2 x i33> [[A:%.*]], <i33 6, i33 5>
|
|
; CHECK-NEXT: [[C:%.*]] = shl <2 x i33> [[B]], <i33 27, i33 28>
|
|
; CHECK-NEXT: ret <2 x i33> [[C]]
|
|
;
|
|
%B = shl <2 x i33> %A, <i33 6, i33 5>
|
|
%C = shl <2 x i33> %B, <i33 27, i33 28>
|
|
ret <2 x i33> %C
|
|
}
|
|
|
|
define i232 @lshr_lshr(i232 %A) {
|
|
; CHECK-LABEL: @lshr_lshr(
|
|
; CHECK-NEXT: [[B:%.*]] = lshr i232 [[A:%.*]], 231
|
|
; CHECK-NEXT: [[C:%.*]] = lshr i232 [[B]], 1
|
|
; CHECK-NEXT: ret i232 [[C]]
|
|
;
|
|
%B = lshr i232 %A, 231
|
|
%C = lshr i232 %B, 1
|
|
ret i232 %C
|
|
}
|
|
|
|
define <2 x i32> @lshr_lshr_splat_vec(<2 x i32> %A) {
|
|
; CHECK-LABEL: @lshr_lshr_splat_vec(
|
|
; CHECK-NEXT: [[B:%.*]] = lshr <2 x i32> [[A:%.*]], <i32 28, i32 28>
|
|
; CHECK-NEXT: [[C:%.*]] = lshr <2 x i32> [[B]], <i32 4, i32 4>
|
|
; CHECK-NEXT: ret <2 x i32> [[C]]
|
|
;
|
|
%B = lshr <2 x i32> %A, <i32 28, i32 28>
|
|
%C = lshr <2 x i32> %B, <i32 4, i32 4>
|
|
ret <2 x i32> %C
|
|
}
|
|
|
|
define <2 x i32> @lshr_lshr_vec(<2 x i32> %A) {
|
|
; CHECK-LABEL: @lshr_lshr_vec(
|
|
; CHECK-NEXT: [[B:%.*]] = lshr <2 x i32> [[A:%.*]], <i32 29, i32 28>
|
|
; CHECK-NEXT: [[C:%.*]] = lshr <2 x i32> [[B]], <i32 4, i32 5>
|
|
; CHECK-NEXT: ret <2 x i32> [[C]]
|
|
;
|
|
%B = lshr <2 x i32> %A, <i32 29, i32 28>
|
|
%C = lshr <2 x i32> %B, <i32 4, i32 5>
|
|
ret <2 x i32> %C
|
|
}
|
|
|