<html>
<head>
<base href="https://llvm.org/bugs/" />
</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 --- - [Cyclone] Register spills related to FeatureZCZeroing"
href="https://llvm.org/bugs/show_bug.cgi?id=27454">27454</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>[Cyclone] Register spills related to FeatureZCZeroing
</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>Linux
</td>
</tr>
<tr>
<th>Status</th>
<td>NEW
</td>
</tr>
<tr>
<th>Severity</th>
<td>normal
</td>
</tr>
<tr>
<th>Priority</th>
<td>P
</td>
</tr>
<tr>
<th>Component</th>
<td>Backend: AArch64
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>haicheng@codeaurora.org
</td>
</tr>
<tr>
<th>CC</th>
<td>gberry@codeaurora.org, llvm-bugs@lists.llvm.org, mcrosier@codeaurora.org
</td>
</tr>
<tr>
<th>Classification</th>
<td>Unclassified
</td>
</tr></table>
<p>
<div>
<pre>Created <span class=""><a href="attachment.cgi?id=16245" name="attach_16245" title="a .ll test case that has extra register spills if using -mcpu=cyclone">attachment 16245</a> <a href="attachment.cgi?id=16245&action=edit" title="a .ll test case that has extra register spills if using -mcpu=cyclone">[details]</a></span>
a .ll test case that has extra register spills if using -mcpu=cyclone
I am trying to port FeatureZCZeroing from Cyclone to Kryo. Using immediate #0
to zero out W and X registers works great in Kryo. But using #0 to zero out
float registers sometimes causes extra register spills or move instructions on
either Cyclone or Kryo.
I attached a reduced IR test case which basically corresponds to the following
C code
double foo(int n) {
double r=-10000;
for (int i=0;i<n;i++) {
x = sin(i);
r = max(r,x);
}
return(-r);
}
If compiled towards Cyclone, the loop body has one spill and two reloads as
below
.LBB0_1: // %for.body
// =>This Inner Loop Header: Depth=1
str q0, [sp] // 16-byte Folded Spill
ldr q0, [sp] // 16-byte Folded Reload
bl sin
fmaxnm d8, d8, d0
ldr q0, [sp] // 16-byte Folded Reload
fadd d0, d0, d9
add w20, w20, #1 // =1
cmp w20, w19
b.lt .LBB0_1
If FeatureZCZeroing is disabled (together with FeatureZCRegMove) on Cyclone,
the translated assembly does not have these load/store instructions:
.LBB0_1: // %for.body
// =>This Inner Loop Header: Depth=1
mov v0.16b, v8.16b
bl sin
fmaxnm d9, d9, d0
fadd d8, d8, d10
add w20, w20, #1 // =1
cmp w20, w19
b.lt .LBB0_1</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>