Skip to content

OpenCL: rename Z61 fma() to z61_fma() for AMD COMGR overload resolution #2

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
jcoxdco wants to merge 1 commit into
base: master
Choose a base branch
from
Open

OpenCL: rename Z61 fma() to z61_fma() for AMD COMGR overload resolution #2

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions src/cl/math.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -820,7 +820,7 @@ Z61 OVERLOAD mul(Z61 a, Z61 b) {
return add(lo61, hi61);
}

Z61 OVERLOAD fma(Z61 a, Z61 b, Z61 c) { return add(mul(a, b), c); } // GWBUG: Can we do better?
Z61 OVERLOAD z61_fma(Z61 a, Z61 b, Z61 c) { return add(mul(a, b), c); } // GWBUG: Can we do better? (Not named fma: clashes with float fma on some OpenCL compilers.)

// Multiply by 2
Z61 OVERLOAD mul2(Z61 a) { return ((a + a) + (a >> 60)) & M61; } // GWBUG: Make sure "+ a>>60" does an add to lower u32 without a followup adc.
Expand Down Expand Up @@ -962,7 +962,7 @@ Z61 OVERLOAD weakMul(Z61 a, Z61 b, const u32 a_m61_count, const u32 b_m61_count)

Z61 OVERLOAD mul(Z61 a, Z61 b) { return modM61(weakMul(a, b, 2, 2)); }

Z61 OVERLOAD fma(Z61 a, Z61 b, Z61 c) { return modM61(weakMul(a, b, 2, 2) + c); } // GWBUG: Can we do better?
Z61 OVERLOAD z61_fma(Z61 a, Z61 b, Z61 c) { return modM61(weakMul(a, b, 2, 2) + c); } // GWBUG: Can we do better? (Not named fma: clashes with float fma on some OpenCL compilers.)

// Multiply by 2
Z61 OVERLOAD mul2(Z61 a) { return add(a, a); }
Expand Down