https://bugs.llvm.org/show_bug.cgi?id=49739
Bug ID: 49739
Summary: [Matrix] Support #pragma clang fp
Product: clang
Version: unspecified
Hardware: PC
OS: All
Status: NEW
Severity: enhancement
Priority: P
Component: LLVM Codegen
Assignee: unassignedclangb...@nondot.org
Reporter: florian_h...@apple.com
CC: llvm-bugs@lists.llvm.org, neeil...@live.com,
richard-l...@metafoo.co.uk
Currently, `#pragma clang fp` are ignored for matrix types.
For the code below, the `contract` fast-math flag should be added to the
generated call to `llvm.matrix.multiply` and `fadd` (see also
https://godbolt.org/z/PEW8aaPoq)
typedef float fx2x2_t __attribute__((matrix_type(2, 2)));
void foo(fx2x2_t &A, fx2x2_t &C, fx2x2_t &B) {
#pragma clang fp contract(fast)
C = A*B + C;
}
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs