<html>
<head>
<base href="https://bugs.llvm.org/">
</head>
<body><table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Bug ID</th>
<td><a class="bz_bug_link
bz_status_NEW "
title="NEW - [Matrix] LowerMatrixIntrinsics should preserve existing fast-math flags during lowering"
href="https://bugs.llvm.org/show_bug.cgi?id=49738">49738</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>[Matrix] LowerMatrixIntrinsics should preserve existing fast-math flags during lowering
</td>
</tr>
<tr>
<th>Product</th>
<td>libraries
</td>
</tr>
<tr>
<th>Version</th>
<td>trunk
</td>
</tr>
<tr>
<th>Hardware</th>
<td>PC
</td>
</tr>
<tr>
<th>OS</th>
<td>All
</td>
</tr>
<tr>
<th>Status</th>
<td>NEW
</td>
</tr>
<tr>
<th>Severity</th>
<td>enhancement
</td>
</tr>
<tr>
<th>Priority</th>
<td>P
</td>
</tr>
<tr>
<th>Component</th>
<td>Scalar Optimizations
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>florian_hahn@apple.com
</td>
</tr>
<tr>
<th>CC</th>
<td>llvm-bugs@lists.llvm.org
</td>
</tr></table>
<p>
<div>
<pre>Currently LowerMatrixIntrinsics does not add existing fast-math flags from
matrix intrinsics & other instructions with shape information to the lowered
instructions.
For the example below, `opt -lower-matrix-intrinsics` creates fmuladd/fadd/fmul
instructions without `fast`: <a href="https://godbolt.org/z/1o48Tx1bP">https://godbolt.org/z/1o48Tx1bP</a>
This also means we fail to fold redundant FP instructions. In this case, we end
up with fmuladd calls with operands that are zero and can be simplified with
`fast`: <a href="https://godbolt.org/z/5oWs1oh91">https://godbolt.org/z/5oWs1oh91</a>
define <4 x float> @foo(<4 x float> %m, float %x, float %y) {
%i1 = insertelement <4 x float> <float poison, float 0.000000e+00, float
0.000000e+00, float poison>, float %x, i64 0
%i2 = insertelement <4 x float> %i1, float %y, i64 3
%res = tail call fast <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4
x float> %m, <4 x float> %i1, i32 2, i32 2, i32 2)
%res.2 = fadd fast <4 x float> %res, %m
ret <4 x float> %res
}
declare <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4 x float>, <4 x
float>, i32, i32, i32)</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are on the CC list for the bug.</li>
</ul>
</body>
</html>