Question

Vector by Scalar Division with -ffast-math

score 30 · Answer 1 · 2024-03-30T21:47:04.273000

30

Views

Vector by Scalar Division with -ffast-math

Published on 30 March 2024 at 21:47

score 141 · Answer 2 · 2024-01-26T21:48:02.550000

141

Views

C++ Eigen::inverse function renders totally wrong array with ffast-math option

Published on 26 January 2024 at 21:48

score 80 · Answer 3 · 2024-01-08T15:53:29.713000

80

Views

Which specific optimization flag causes libm functions to be treated as pure?

Published on 08 January 2024 at 15:53

score 177 · Answer 4 · 2023-06-21T17:18:21.890000

177

Views

How can I find math operations that would be optimized by `-ffast-math`?

Published on 21 June 2023 at 17:18

score 364 · Answer 5 · 2023-04-19T13:23:12.307000

364

Views

Why can't the Rust compiler auto-vectorize this FP dot product implementation?

Published on 19 April 2023 at 13:23

score 187 · Answer 6 · 2022-10-28T02:13:57.313000

187

Views

Fortran code compiled in one Windows machine (2018 Intel processor) gives different results when exe is copied to other machine (2022 Intel processor)

Published on 28 October 2022 at 02:13

score 145 · Answer 7 · 2022-06-28T09:57:52.500000

145

Views

Weird LTO behavior with -ffast-math

Published on 28 June 2022 at 09:57

score 212 · Answer 8 · 2022-06-09T09:16:36.537000

212

Views

C++ gcc does associative-math flag disable float NAN values?

Published on 09 June 2022 at 09:16

score 159 · Answer 9 · 2021-12-06T14:40:49.913000

159

Views

Why does -fno-signed-zeros have an effect on vectorization for minimum search?

Published on 06 December 2021 at 14:40

score 240 · Answer 10 · 2021-05-13T22:26:13.370000

240

Views

Is there a way to tell the compiler to compile with "fast-math" or something similar in C#?

Published on 13 May 2021 at 22:26

score 237 · Answer 11 · 2021-05-10T09:13:54.443000

237

Views

Where is the source of imprecise calculation in the assembler code of gcc -Ofast compared with -O3?

Published on 10 May 2021 at 09:13

score 123 · Answer 12 · 2020-05-21T21:23:10.193000

123

Views

Can this piece of code be modified such that it works with fast-math enabled?

Published on 21 May 2020 at 21:23

score 410 · Answer 13 · 2020-04-27T11:35:16.503000

410

Views

What does the "denormal input" exactly mean in assembly when we consider using DAZ flag for SSE Floating Points

Published on 27 April 2020 at 11:35

score 468 · Answer 14 · 2020-04-06T11:11:20.143000

468

Views

host device functions calling overloaded functions

Published on 06 April 2020 at 11:11

score 1.1k · Answer 15 · 2020-02-10T20:03:59.100000

1.1k

Views

Can I determine at compile time whether --use_fast_math was set?

Published on 10 February 2020 at 20:03

score 1.9k · Answer 16 · 2019-08-01T03:51:07.393000

1.9k

Views

Optimal implementation of iterative Kahan summation

Published on 01 August 2019 at 03:51

score 248 · Answer 17 · 2019-07-09T12:13:55.183000

248

Views

Flag to generate 'deterministic' floating point operations wrt. pointer alignment with 'fast-math'?

Published on 09 July 2019 at 12:13

score 401 · Answer 18 · 2019-04-11T11:00:16.113000

401

Views

Does GCC's ffast-math have consistency guarantees across platforms or compiler versions?

Published on 11 April 2019 at 11:00

score 724 · Answer 19 · 2019-01-04T23:13:57.233000

724

Views

Do denormal flags like Denormals-Are-Zero (DAZ) affect comparisons for equality?

Published on 04 January 2019 at 23:13

score 2.3k · Answer 20 · 2017-05-23T11:51:22.643000

2.3k

Views

Strict aliasing, -ffast-math and SSE

Published on 23 May 2017 at 11:51

List Question

Vector by Scalar Division with -ffast-math

C++ Eigen::inverse function renders totally wrong array with ffast-math option

Which specific optimization flag causes libm functions to be treated as pure?

How can I find math operations that would be optimized by `-ffast-math`?

Why can't the Rust compiler auto-vectorize this FP dot product implementation?

Fortran code compiled in one Windows machine (2018 Intel processor) gives different results when exe is copied to other machine (2022 Intel processor)

Weird LTO behavior with -ffast-math

C++ gcc does associative-math flag disable float NAN values?

Why does -fno-signed-zeros have an effect on vectorization for minimum search?

Is there a way to tell the compiler to compile with "fast-math" or something similar in C#?

Where is the source of imprecise calculation in the assembler code of gcc -Ofast compared with -O3?

Can this piece of code be modified such that it works with fast-math enabled?

What does the "denormal input" exactly mean in assembly when we consider using DAZ flag for SSE Floating Points

host device functions calling overloaded functions

Can I determine at compile time whether --use_fast_math was set?

Optimal implementation of iterative Kahan summation

Flag to generate 'deterministic' floating point operations wrt. pointer alignment with 'fast-math'?

Does GCC's ffast-math have consistency guarantees across platforms or compiler versions?

Do denormal flags like Denormals-Are-Zero (DAZ) affect comparisons for equality?

Strict aliasing, -ffast-math and SSE

Trending Questions

Popular # Hahtags

Popular Questions