Skip to content

[HIP] Add execution test for setcc f64 -> setcc i32 reduction#378

Open
zGoldthorpe wants to merge 3 commits intollvm:mainfrom
zGoldthorpe:pr188356
Open

[HIP] Add execution test for setcc f64 -> setcc i32 reduction#378
zGoldthorpe wants to merge 3 commits intollvm:mainfrom
zGoldthorpe:pr188356

Conversation

@zGoldthorpe
Copy link
Copy Markdown

Adds a test to measure the performance effects of llvm/llvm-project#188356.

Comment thread External/HIP/simplify-f64-cmps.hip Outdated
Comment thread External/HIP/simplify-f64-cmps.hip Outdated
static constexpr size_t Iterations = 4096;

__host__ __device__ void fold(uint8_t sel, double x, double *y) {
double split = sel ? 1.0 : 4.0;
Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Should test more cases, especially non-inline immediates

Note that upper bound for lt comparisons must be guaranteed nnan (and
moreover this needs to be recognised by the optimisation, which
currently uses computeKnownBits)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants