Skip to content

[DemandedBits] Add div/rem support #148853

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 9 commits into
base: main
Choose a base branch
from
+97 −0
Open

[DemandedBits] Add div/rem support #148853

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
78db179
[LLVM] DemandedBits: Propagate demanded bits through div/rem ops
karouzakisp Jul 15, 2025
6d9b271
[LLVM] used APInt's API to be safe with from larger than 64 bits div/…
karouzakisp Jul 15, 2025
d2df527
minor updates and added new test that was supposed to be failing
karouzakisp Jul 16, 2025
e1c0bde
fixed Check-Label
karouzakisp Jul 16, 2025
179eb22
fixed srem, we need to preserve the sign bit, otherwise we might lose it
karouzakisp Jul 16, 2025
216f44b
removed risky demanded bits propagation with division
karouzakisp Jul 16, 2025
aada689
set sign bit on sdiv and srem to avoid missing the sign bit
karouzakisp Jul 16, 2025
64b366f
removed sdiv, udiv, urem
karouzakisp Jul 23, 2025
80d03bf
updated test
karouzakisp Jul 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
54 changes: 54 additions & 0 deletions llvm/lib/Analysis/DemandedBits.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@
#include "llvm/Support/Casting.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/KnownBits.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cstdint>
Expand Down Expand Up @@ -246,6 +247,59 @@ void DemandedBits::determineLiveOperandBits(
else
AB &= ~(Known.One & ~Known2.One);
break;
case Instruction::SRem:
case Instruction::URem:
case Instruction::UDiv:
case Instruction::SDiv: {
auto Opc = UserI->getOpcode();
auto IsDiv = Opc == Instruction::UDiv || Opc == Instruction::SDiv;
bool IsSigned = Opc == Instruction::SDiv || Opc == Instruction::SRem;
if (OperandNo == 0) {
const APInt *DivAmnt;
if (match(UserI->getOperand(1), m_APInt(DivAmnt))) {
uint64_t D = DivAmnt->getZExtValue();
if (DivAmnt->isPowerOf2()) {
unsigned Sh = DivAmnt->countr_zero();
if (IsDiv) {
AB = AOut.shl(Sh);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not correct for signed division. Simple example:

(-1 s/ 2) & 1 is 0.
(-1&2 s/ 2) & 1 is 1.

} else {
AB = AOut & APInt::getLowBitsSet(BitWidth, Sh);
}
} else if (IsDiv) { // Non power of 2 constant div
// x = q * C + r;
// q = x / C;
// We think of it like grade school division in base 2.
//
// x = [ unused | window m-bits | ... | needed bits ]
// ^ each step emits 1 quotient bit
// |
// |
// C fits in m = ⌈log2 C⌉ bits
// Each new quotient bit consumes the window of m low bits and
// shifts one position left.

// To produce the first LowQ quotient/rem bits we slide the window
// LowQ times --> need at most LowQ + m low bits of the dividend.
// Need = LowQ + Ceil(log2(C)) (+1 sign bit for
// sdiv/srem). For example : Assume x = b7 b6 b5 b4 b3 b2 b1 b0.
// LowQ = 4, C = 5 and ceil(log_2(C)) = 3.
// step 0: b2 b1 b0, produces quotient q[0].
// step 1: b3 b2 b1, produces quotient q[1].
// step 2: b4 b3 b2, produces quotient q[2].
// step 3: b5 b4 b3, produces quotient q[3].
// k = LowQ - 1;
// TopIndex = k + m-1 = 3 + 2 = 5;
// The dividend bits b5...b0 are enough we don't care for b6 and b7.
unsigned LowQ = AOut.getActiveBits();
unsigned Need = LowQ + DivAmnt->ceilLogBase2();
if (IsSigned)
Need++;
AB = APInt::getLowBitsSet(BitWidth, std::min(BitWidth, Need));
}
}
}
break;
}
case Instruction::Xor:
case Instruction::PHI:
AB = AOut;
Expand Down
266 changes: 266 additions & 0 deletions llvm/test/Analysis/DemandedBits/div_rem.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,266 @@
; RUN: opt -S -disable-output -passes="print<demanded-bits>" < %s 2>&1 | FileCheck %s

define i8 @test_sdiv_const_amount_4(i32 %a) {
; CHECK-LABEL: 'test_sdiv_const_amount_4'
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div = sdiv i32 %a, 4
; CHECK-DAG: DemandedBits: 0x3fc for %a in %div = sdiv i32 %a, 4
; CHECK-DAG: DemandedBits: 0xffffffff for 4 in %div = sdiv i32 %a, 4
;
%div = sdiv i32 %a, 4
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_sdiv_const_amount_5(i32 %a) {
; CHECK-LABEL: 'test_sdiv_const_amount_5'
; CHECK-DAG: DemandedBits: 0xff for %div = sdiv i32 %a, 5
; CHECK-DAG: DemandedBits: 0xfff for %a in %div = sdiv i32 %a, 5
; CHECK-DAG: DemandedBits: 0xffffffff for 5 in %div = sdiv i32 %a, 5
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
;
%div = sdiv i32 %a, 5
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_sdiv_const_amount_8(i32 %a) {
; CHECK-LABEL: 'test_sdiv_const_amount_8'
; CHECK-DAG: DemandedBits: 0xff for %div = sdiv i32 %a, 8
; CHECK-DAG: DemandedBits: 0x7f8 for %a in %div = sdiv i32 %a, 8
; CHECK-DAG: DemandedBits: 0xffffffff for 8 in %div = sdiv i32 %a, 8
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
;
%div = sdiv i32 %a, 8
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_sdiv_const_amount_9(i32 %a) {
; CHECK-LABEL: 'test_sdiv_const_amount_9'
; CHECK-DAG: DemandedBits: 0xff for %div = udiv i32 %a, 9
; CHECK-DAG: DemandedBits: 0xfff for %a in %div = udiv i32 %a, 9
; CHECK-DAG: DemandedBits: 0xffffffff for 9 in %div = udiv i32 %a, 9
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
;
%div = udiv i32 %a, 9
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_sdiv(i32 %a, i32 %b) {
; CHECK-LABEL: 'test_sdiv'
; CHECK-DAG: DemandedBits: 0xff for %div = sdiv i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %div = sdiv i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %b in %div = sdiv i32 %a, %b
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
;
%div = sdiv i32 %a, %b
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_udiv_const_amount_4(i32 %a) {
; CHECK-LABEL: 'test_udiv_const_amount_4'
; CHECK-DAG: DemandedBits: 0xff for %div = udiv i32 %a, 4
; CHECK-DAG: DemandedBits: 0x3fc for %a in %div = udiv i32 %a, 4
; CHECK-DAG: DemandedBits: 0xffffffff for 4 in %div = udiv i32 %a, 4
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
;
%div = udiv i32 %a, 4
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_udiv_const_amount_5(i32 %a) {
; CHECK-LABEL: 'test_udiv_const_amount_5'
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div = udiv i32 %a, 5
; CHECK-DAG: DemandedBits: 0x7ff for %a in %div = udiv i32 %a, 5
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's imagine %a is 0xfffffff. 0xffffffff/0x5 is 0x33333333.

This is saying that we're allowed to treat %a as 0x7ff because the upper bits don't matter. 0x7ff/0x5 is 0x199. That's a different value in bits 7:0 than the 0x33333333.

What am I missing?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That's correct, when developing the algorithm, I assumed Knuth-like division, which isn't exactly accurate, and bit-by-bit recurrence. Real division isn't exactly like this.

; CHECK-DAG: DemandedBits: 0xffffffff for 5 in %div = udiv i32 %a, 5
;
%div = udiv i32 %a, 5
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_udiv_const_amount_8(i32 %a) {
; CHECK-LABEL: 'test_udiv_const_amount_8'
; CHECK-DAG: DemandedBits: 0xff for %div = udiv i32 %a, 8
; CHECK-DAG: DemandedBits: 0x7f8 for %a in %div = udiv i32 %a, 8
; CHECK-DAG: DemandedBits: 0xffffffff for 8 in %div = udiv i32 %a, 8
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
;
%div = udiv i32 %a, 8
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_udiv_const_amount_9(i32 %a) {
; CHECK-LABEL: 'test_udiv_const_amount_9'
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div = udiv i32 %a, 9
; CHECK-DAG: DemandedBits: 0xfff for %a in %div = udiv i32 %a, 9
; CHECK-DAG: DemandedBits: 0xffffffff for 9 in %div = udiv i32 %a, 9
;
%div = udiv i32 %a, 9
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_udiv(i32 %a, i32 %b) {
; CHECK-LABEL: 'test_udiv'
; CHECK-DAG: DemandedBits: 0xff for %div = udiv i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %div = udiv i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %b in %div = udiv i32 %a, %b
; CHECK-DAG: DemandedBits: 0xff for %div.t = trunc i32 %div to i8
; CHECK-DAG: DemandedBits: 0xff for %div in %div.t = trunc i32 %div to i8
;
%div = udiv i32 %a, %b
%div.t = trunc i32 %div to i8
ret i8 %div.t
}

define i8 @test_srem_const_amount_4(i32 %a) {
; CHECK-LABEL: 'test_srem_const_amount_4'
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem = srem i32 %a, 4
; CHECK-DAG: DemandedBits: 0x3 for %a in %rem = srem i32 %a, 4
; CHECK-DAG: DemandedBits: 0xffffffff for 4 in %rem = srem i32 %a, 4
;
%rem = srem i32 %a, 4
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_srem_const_amount_5(i32 %a) {
; CHECK-LABEL: 'test_srem_const_amount_5'
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem = srem i32 %a, 5
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %rem = srem i32 %a, 5
; CHECK-DAG: DemandedBits: 0xffffffff for 5 in %rem = srem i32 %a, 5
;
%rem = srem i32 %a, 5
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_srem_const_amount_8(i32 %a) {
; CHECK-LABEL: 'test_srem_const_amount_8'
; CHECK-DAG: DemandedBits: 0xff for %rem = srem i32 %a, 8
; CHECK-DAG: DemandedBits: 0x7 for %a in %rem = srem i32 %a, 8
; CHECK-DAG: DemandedBits: 0xffffffff for 8 in %rem = srem i32 %a, 8
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
;
%rem = srem i32 %a, 8
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_srem_const_amount_9(i32 %a) {
; CHECK-LABEL: 'test_srem_const_amount_9'
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem = srem i32 %a, 9
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %rem = srem i32 %a, 9
; CHECK-DAG: DemandedBits: 0xffffffff for 9 in %rem = srem i32 %a, 9
;
%rem = srem i32 %a, 9
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_srem(i32 %a, i32 %b) {
; CHECK-LABEL: 'test_srem'
; CHECK-DAG: DemandedBits: 0xff for %rem = srem i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %rem = srem i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %b in %rem = srem i32 %a, %b
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
;
%rem = srem i32 %a, %b
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_urem_const_amount_4(i32 %a) {
; CHECK-LABEL: 'test_urem_const_amount_4'
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem = urem i32 %a, 4
; CHECK-DAG: DemandedBits: 0x3 for %a in %rem = urem i32 %a, 4
; CHECK-DAG: DemandedBits: 0xffffffff for 4 in %rem = urem i32 %a, 4
;
%rem = urem i32 %a, 4
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}






define i8 @test_urem_const_amount_5(i32 %a) {
; CHECK-LABEL: 'test_urem_const_amount_5'
; CHECK-DAG: DemandedBits: 0xff for %rem = urem i32 %a, 5
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %rem = urem i32 %a, 5
; CHECK-DAG: DemandedBits: 0xffffffff for 5 in %rem = urem i32 %a, 5
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
;
%rem = urem i32 %a, 5
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_urem_const_amount_8(i32 %a) {
; CHECK-LABEL: 'test_urem_const_amount_8'
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem = urem i32 %a, 8
; CHECK-DAG: DemandedBits: 0x7 for %a in %rem = urem i32 %a, 8
; CHECK-DAG: DemandedBits: 0xffffffff for 8 in %rem = urem i32 %a, 8
;
%rem = urem i32 %a, 8
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_urem_const_amount_9(i32 %a) {
; CHECK-LABEL: 'test_urem_const_amount_9'
; CHECK-DAG: DemandedBits: 0xff for %rem = urem i32 %a, 9
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %rem = urem i32 %a, 9
; CHECK-DAG: DemandedBits: 0xffffffff for 9 in %rem = urem i32 %a, 9
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
;
%rem = urem i32 %a, 9
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}

define i8 @test_urem(i32 %a, i32 %b) {
; CHECK-LABEL: 'test_urem'
; CHECK-DAG: DemandedBits: 0xff for %rem = urem i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %a in %rem = urem i32 %a, %b
; CHECK-DAG: DemandedBits: 0xffffffff for %b in %rem = urem i32 %a, %b
; CHECK-DAG: DemandedBits: 0xff for %rem.t = trunc i32 %rem to i8
; CHECK-DAG: DemandedBits: 0xff for %rem in %rem.t = trunc i32 %rem to i8
;
%rem = urem i32 %a, %b
%rem.t = trunc i32 %rem to i8
ret i8 %rem.t
}