<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="/rss.xsl.xml"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/">
<channel>
    <title>Changes in image-schedule.ll</title>
    <description></description>
    <language>en</language>
    <copyright>Copyright 2015</copyright>
    <generator>Java</generator><item>
        <title>9de2fb58 - AMDGPU: Fix some outdated datalayouts in tests</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll#9de2fb58</link>
        <description>AMDGPU: Fix some outdated datalayouts in testsllvm-svn: 342131

            List of files:
            /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll</description>
        <pubDate>Thu, 13 Sep 2018 11:56:28 +0000</pubDate>
        <dc:creator>Matt Arsenault &lt;Matthew.Arsenault@amd.com&gt;</dc:creator>
    </item>
<item>
        <title>1045928a - AMDGPU: Convert test cases to the dimension-aware intrinsics</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll#1045928a</link>
        <description>AMDGPU: Convert test cases to the dimension-aware intrinsicsSummary:Also explicitly port over some tests in llvm.amdgcn.image.* that weremissing. Some tests are removed because they no longer apply (i.e.explicitly testing building an address vector via insertelement).This is in preparation for the eventual removal of the old-styleintrinsics.Some additional notes:- constant-address-space-32bit.ll: change some GCN-NEXT to GCN because  the instruction schedule was subtly altered- insert_vector_elt.ll: the old test didn&apos;t actually test anything,  because %tmp1 was not used; remove the load, because it doesn&apos;t work  (Because of the amdgpu_ps calling convention? In any case, it&apos;s  orthogonal to what the test claims to be testing.)Change-Id: Idfa99b6512ad139e755e82b8b89548ab08f0afcfReviewers: arsenm, rampitecSubscribers: MatzeB, qcolombet, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commitsDifferential Revision: https://reviews.llvm.org/D48018llvm-svn: 335229

            List of files:
            /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll</description>
        <pubDate>Thu, 21 Jun 2018 13:37:19 +0000</pubDate>
        <dc:creator>Nicolai Haehnle &lt;nhaehnle@gmail.com&gt;</dc:creator>
    </item>
<item>
        <title>0124b548 - [AMDGPU] Change constant addr space to 4</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll#0124b548</link>
        <description>[AMDGPU] Change constant addr space to 4Differential Revision: https://reviews.llvm.org/D43170llvm-svn: 325030

            List of files:
            /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll</description>
        <pubDate>Tue, 13 Feb 2018 18:00:25 +0000</pubDate>
        <dc:creator>Yaxun Liu &lt;Yaxun.Liu@amd.com&gt;</dc:creator>
    </item>
<item>
        <title>75ced9d5 - [AMDGPU] stop image_store being moved illegally</title>
        <link>http://172.16.0.5:8080/history/llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll#75ced9d5</link>
        <description>[AMDGPU] stop image_store being moved illegallySummary:A recent change321556: AMDGPU: Remove mayLoad/hasSideEffects from MIMG storescan allow the machine instruction scheduler to move an image store pastan image load using the same descriptor.V2: Fixed by marking image ops as mayAlias and isAliased. This may beoverly conservative, and we may need to revisit.V3: Reverted test change done on 321556.Reviewers: arsenm, nhaehnle, dstuttardSubscribers: llvm-commits, t-tye, yaxunl, wdng, kzhuravlDifferential Revision: https://reviews.llvm.org/D41969llvm-svn: 322419

            List of files:
            /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/image-schedule.ll</description>
        <pubDate>Fri, 12 Jan 2018 22:57:24 +0000</pubDate>
        <dc:creator>Tim Renouf &lt;tpr.llvm@botech.co.uk&gt;</dc:creator>
    </item>
</channel>
</rss>
