Skip to content
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.

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

Jump to bottom

[SR-11640] Multiplying doubles from struct #54051

Open
zoecarver opened this issue Oct 19, 2019 · 4 comments
Open

[SR-11640] Multiplying doubles from struct #54051

zoecarver opened this issue Oct 19, 2019 · 4 comments
Labels
CodeGen compiler The Swift compiler in itself improvement performance SILOptimizer Area → compiler: SIL optimization passes

Comments

@zoecarver
Copy link
Collaborator

Previous ID SR-11640
Radar None
Original Reporter @zoecarver
Type Improvement
Additional Detail from JIRA
Votes 0
Component/s Compiler
Labels Improvement, CodeGen, Optimizer, Performance
Assignee None
Priority Medium

md5: 833dd33d195d879e7d8fc3c9618b65e2

Issue Description:

struct X {
    let x : Double = 2
    let y : Double = 2
    let z : Double = 2
}

func test(numbers: [X]) -> Double {
    var x = 1.0
    for num in numbers {
        x *= num.x
        x *= num.y
        x *= num.z
    }
    return x
}

assert(test(numbers: [X(), X(), X(), X(), X()]) != 0)

The following generates 9 different `fmul` instructions. It should only generate 3. It also generates 31 `getelementptr` instructions when it certainly doesn't need that many, and theoretically could only generate 4.

An equivalent program in C++ takes about 1/4th of the time to run. Here is a comparison of the codegen from swift and clang.

If others agree this is an issue, I will start working on a patch to try to resolve it.
@belkadan
Copy link
Contributor

I only see three fmul instructions in the optimized code. Are you looking at unoptimized code?

@zoecarver
Copy link
Collaborator Author

Yes, I am looking at the optimized code. Take a look at the assembly or the IR gen in the link above.

@belkadan
Copy link
Contributor

Ah, I thought you meant LLVM IR. The nine instructions are from loop unrolling; if you use -Osize instead of -O you get the three you originally expected.

@zoecarver
Copy link
Collaborator Author

Ah, you're right! That's probably not the slow part. I tried removing the conditional fails which made it a little faster but, not much. Any other ideas?

@swift-ci swift-ci transferred this issue from apple/swift-issues Apr 25, 2022
@AnthonyLatsis AnthonyLatsis added SILOptimizer Area → compiler: SIL optimization passes and removed Optimizer labels Nov 3, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
CodeGen compiler The Swift compiler in itself improvement performance SILOptimizer Area → compiler: SIL optimization passes
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@belkadan @zoecarver @AnthonyLatsis