maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/split-smrd.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

43 lines
2.0 KiB
LLVM
Raw Normal View History

AMDGPU: Remove some uses of llvm.SI.export in tests Merge some of the old, smaller tests into more complete versions. llvm-svn: 295792
2017-02-22 08:02:21 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
; FIXME: Move this to sgpr-copy.ll when this is fixed on VI.
; Make sure that when we split an smrd instruction in order to move it to
; the VALU, we are also moving its users to the VALU.
AMDGPU: Remove some uses of llvm.SI.export in tests Merge some of the old, smaller tests into more complete versions. llvm-svn: 295792
2017-02-22 08:02:21 +08:00
; GCN-LABEL: {{^}}split_smrd_add_worklist:
; GCN: image_sample v{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}] dmask:0x1
AMDGPU: Drop remnants of byval support for shaders Before 2018, mesa used to use byval interchangably with inreg, which didn't really make sense. Fix tests still using it to avoid breaking in a future commit. llvm-svn: 365953
2019-07-13 04:12:17 +08:00
define amdgpu_ps void @split_smrd_add_worklist([34 x <8 x i32>] addrspace(4)* inreg %arg) #0 {
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
bb:
AMDGPU: Convert tests away from llvm.SI.load.const llvm-svn: 351494
2019-01-18 06:47:26 +08:00
%tmp = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> undef, i32 96, i32 0)
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
%tmp1 = bitcast float %tmp to i32
br i1 undef, label %bb2, label %bb3
bb2: ; preds = %bb
unreachable
bb3: ; preds = %bb
%tmp4 = bitcast float %tmp to i32
%tmp5 = add i32 %tmp4, 4
%tmp6 = sext i32 %tmp5 to i64
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
%tmp7 = getelementptr [34 x <8 x i32>], [34 x <8 x i32>] addrspace(4)* %arg, i64 0, i64 %tmp6
%tmp8 = load <8 x i32>, <8 x i32> addrspace(4)* %tmp7, align 32, !tbaa !0
AMDGPU: Convert test cases to the dimension-aware intrinsics Summary: Also explicitly port over some tests in llvm.amdgcn.image.* that were missing. 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-style intrinsics. 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't actually test anything, because %tmp1 was not used; remove the load, because it doesn't work (Because of the amdgpu_ps calling convention? In any case, it's orthogonal to what the test claims to be testing.) Change-Id: Idfa99b6512ad139e755e82b8b89548ab08f0afcf Reviewers: arsenm, rampitec Subscribers: MatzeB, qcolombet, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D48018 llvm-svn: 335229
2018-06-21 21:37:19 +08:00
%tmp9 = call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 15, float bitcast (i32 1061158912 to float), float bitcast (i32 1048576000 to float), <8 x i32> %tmp8, <4 x i32> undef, i1 0, i32 0, i32 0)
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
%tmp10 = extractelement <4 x float> %tmp9, i32 0
AMDGPU: Add cvt.pkrtz intrinsic Convert llvm.SI.packf16 test uses llvm-svn: 295797
2017-02-22 08:27:34 +08:00
%tmp12 = call <2 x half> @llvm.amdgcn.cvt.pkrtz(float %tmp10, float undef)
call void @llvm.amdgcn.exp.compr.v2f16(i32 0, i32 15, <2 x half> %tmp12, <2 x half> undef, i1 true, i1 true) #0
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
ret void
}
AMDGPU: Add cvt.pkrtz intrinsic Convert llvm.SI.packf16 test uses llvm-svn: 295797
2017-02-22 08:27:34 +08:00
declare <2 x half> @llvm.amdgcn.cvt.pkrtz(float, float) #1
AMDGPU: Convert image intrinsic uses in tests llvm-svn: 298386
2017-03-22 00:24:12 +08:00
declare void @llvm.amdgcn.exp.compr.v2f16(i32, i32, <2 x half>, <2 x half>, i1, i1) #0
AMDGPU: Convert test cases to the dimension-aware intrinsics Summary: Also explicitly port over some tests in llvm.amdgcn.image.* that were missing. 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-style intrinsics. 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't actually test anything, because %tmp1 was not used; remove the load, because it doesn't work (Because of the amdgpu_ps calling convention? In any case, it's orthogonal to what the test claims to be testing.) Change-Id: Idfa99b6512ad139e755e82b8b89548ab08f0afcf Reviewers: arsenm, rampitec Subscribers: MatzeB, qcolombet, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D48018 llvm-svn: 335229
2018-06-21 21:37:19 +08:00
declare <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #2
AMDGPU: Convert tests away from llvm.SI.load.const llvm-svn: 351494
2019-01-18 06:47:26 +08:00
declare float @llvm.amdgcn.s.buffer.load.f32(<4 x i32>, i32, i32) #1
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
AMDGPU: Remove superfluous string attributes from tests Also fix v_mac.ll not testing right thing for fneg llvm-svn: 275129
2016-07-12 07:35:48 +08:00
attributes #0 = { nounwind }
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
attributes #1 = { nounwind readnone }
AMDGPU: Convert image intrinsic uses in tests llvm-svn: 298386
2017-03-22 00:24:12 +08:00
attributes #2 = { nounwind readonly }
AMDGPU/SI: Make sure MIMG descriptors and samplers stay in SGPRs Summary: It's possible to have resource descriptors and samplers stored in VGPRs, either by a VMEM instruction or in the case of samplers, floating-point calculations. When this happens, we need to use v_readfirstlane to copy these values back to sgprs. Reviewers: mareko, arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17102 llvm-svn: 260599
2016-02-12 05:45:07 +08:00
!0 = !{!1, !1, i64 0, i32 1}
AMDGPU: Remove some uses of llvm.SI.export in tests Merge some of the old, smaller tests into more complete versions. llvm-svn: 295792
2017-02-22 08:02:21 +08:00
!1 = !{!"const", !2}
!2 = !{!"tbaa root"}