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/undefined-subreg-liverange.ll

90 lines
3.0 KiB
LLVM
Raw Normal View History

AMDGPU: Fix verifier error from partially undef copy In this situation: %VGPR2<def> = BUFFER_LOAD_DWORD_OFFSET %SGPR8_SGPR9_SGPR10_SGPR11, %VGPR7<def,tied3> = V_MAC_F32_e32 %VGPR0<undef>, %VGPR1<kill>, %VGPR7<kill,tied0>, %EXEC<imp-use> %VGPR3_VGPR4_VGPR5_VGPR6<def> = COPY %VGPR0_VGPR1_VGPR2_VGPR3 %VGPR4<def> = COPY %VGPR2 The copy for VGPR1 -> VGPR4 was an error from reading undefined VGPR1, but VGPR4 is defined immediately after this copy. llvm-svn: 275635
2016-07-16 06:32:02 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
MachineVerifier: subregs so not require defs/valnos on every path It is fine for subregister ranges to be undefined on some CFG paths as we may have a "vregX:other_subreg<read-undef> =" def on that path. We do not (and should not) have live segments for the subregister ranges. The MachineVerifier should not complain about this. This is a slight variant of http://llvm.org/PR27705 llvm-svn: 270290
2016-05-21 07:02:13 +08:00
; We may have subregister live ranges that are undefined on some paths. The
; verifier should not complain about this.
AMDGPU: Fix verifier error from partially undef copy In this situation: %VGPR2<def> = BUFFER_LOAD_DWORD_OFFSET %SGPR8_SGPR9_SGPR10_SGPR11, %VGPR7<def,tied3> = V_MAC_F32_e32 %VGPR0<undef>, %VGPR1<kill>, %VGPR7<kill,tied0>, %EXEC<imp-use> %VGPR3_VGPR4_VGPR5_VGPR6<def> = COPY %VGPR0_VGPR1_VGPR2_VGPR3 %VGPR4<def> = COPY %VGPR2 The copy for VGPR1 -> VGPR4 was an error from reading undefined VGPR1, but VGPR4 is defined immediately after this copy. llvm-svn: 275635
2016-07-16 06:32:02 +08:00
; CHECK-LABEL: {{^}}func:
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @func() #0 {
MachineVerifier: subregs so not require defs/valnos on every path It is fine for subregister ranges to be undefined on some CFG paths as we may have a "vregX:other_subreg<read-undef> =" def on that path. We do not (and should not) have live segments for the subregister ranges. The MachineVerifier should not complain about this. This is a slight variant of http://llvm.org/PR27705 llvm-svn: 270290
2016-05-21 07:02:13 +08:00
B0:
br i1 undef, label %B1, label %B2
B1:
br label %B2
B2:
%v0 = phi <4 x float> [ zeroinitializer, %B1 ], [ <float 0.0, float 0.0, float 0.0, float undef>, %B0 ]
br i1 undef, label %B30.1, label %B30.2
B30.1:
%sub = fsub <4 x float> %v0, undef
br label %B30.2
B30.2:
%v3 = phi <4 x float> [ %sub, %B30.1 ], [ %v0, %B2 ]
%ve0 = extractelement <4 x float> %v3, i32 0
store float %ve0, float addrspace(3)* undef, align 4
ret void
}
AMDGPU: Fix verifier error from partially undef copy In this situation: %VGPR2<def> = BUFFER_LOAD_DWORD_OFFSET %SGPR8_SGPR9_SGPR10_SGPR11, %VGPR7<def,tied3> = V_MAC_F32_e32 %VGPR0<undef>, %VGPR1<kill>, %VGPR7<kill,tied0>, %EXEC<imp-use> %VGPR3_VGPR4_VGPR5_VGPR6<def> = COPY %VGPR0_VGPR1_VGPR2_VGPR3 %VGPR4<def> = COPY %VGPR2 The copy for VGPR1 -> VGPR4 was an error from reading undefined VGPR1, but VGPR4 is defined immediately after this copy. llvm-svn: 275635
2016-07-16 06:32:02 +08:00
; FIXME: Extra undef subregister copy should be removed before
; overwritten with defined copy
; CHECK-LABEL: {{^}}valley_partially_undef_copy:
define amdgpu_ps float @valley_partially_undef_copy() #0 {
bb:
%tmp = load volatile i32, i32 addrspace(1)* undef, align 4
%tmp1 = load volatile i32, i32 addrspace(1)* undef, align 4
%tmp2 = insertelement <4 x i32> undef, i32 %tmp1, i32 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
%tmp3 = bitcast i32 %tmp1 to float
%tmp4 = call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 15, float %tmp3, float %tmp3, <8 x i32> undef, <4 x i32> undef, i1 0, i32 0, i32 0)
AMDGPU: Fix verifier error from partially undef copy In this situation: %VGPR2<def> = BUFFER_LOAD_DWORD_OFFSET %SGPR8_SGPR9_SGPR10_SGPR11, %VGPR7<def,tied3> = V_MAC_F32_e32 %VGPR0<undef>, %VGPR1<kill>, %VGPR7<kill,tied0>, %EXEC<imp-use> %VGPR3_VGPR4_VGPR5_VGPR6<def> = COPY %VGPR0_VGPR1_VGPR2_VGPR3 %VGPR4<def> = COPY %VGPR2 The copy for VGPR1 -> VGPR4 was an error from reading undefined VGPR1, but VGPR4 is defined immediately after this copy. llvm-svn: 275635
2016-07-16 06:32:02 +08:00
%tmp5 = extractelement <4 x float> %tmp4, i32 0
%tmp6 = fmul float %tmp5, undef
%tmp7 = fadd float %tmp6, %tmp6
%tmp8 = insertelement <4 x i32> %tmp2, i32 %tmp, i32 1
store <4 x i32> %tmp8, <4 x i32> addrspace(1)* undef, align 16
store float %tmp7, float addrspace(1)* undef, align 4
br label %bb9
bb9: ; preds = %bb9, %bb
%tmp10 = icmp eq i32 %tmp, 0
br i1 %tmp10, label %bb9, label %bb11
bb11: ; preds = %bb9
store <4 x i32> %tmp2, <4 x i32> addrspace(1)* undef, align 16
ret float undef
}
; FIXME: Should be able to remove the undef copies
; CHECK-LABEL: {{^}}partially_undef_copy:
; CHECK: v_mov_b32_e32 v5, 5
; CHECK: v_mov_b32_e32 v6, 6
; CHECK: v_mov_b32_e32 v[[OUTPUT_LO:[0-9]+]], v5
; Undef copy
; CHECK: v_mov_b32_e32 v1, v6
; undef copy
; CHECK: v_mov_b32_e32 v2, v7
; CHECK: v_mov_b32_e32 v[[OUTPUT_HI:[0-9]+]], v8
; CHECK: v_mov_b32_e32 v[[OUTPUT_LO]], v6
; CHECK: buffer_store_dwordx4 v{{\[}}[[OUTPUT_LO]]:[[OUTPUT_HI]]{{\]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @partially_undef_copy() #0 {
AMDGPU: Use correct register names in inline assembly Fixes using physical registers in inline asm from clang. llvm-svn: 305004
2017-06-09 03:03:20 +08:00
%tmp0 = call i32 asm sideeffect "v_mov_b32_e32 v5, 5", "={v5}"()
%tmp1 = call i32 asm sideeffect "v_mov_b32_e32 v6, 6", "={v6}"()
AMDGPU: Fix verifier error from partially undef copy In this situation: %VGPR2<def> = BUFFER_LOAD_DWORD_OFFSET %SGPR8_SGPR9_SGPR10_SGPR11, %VGPR7<def,tied3> = V_MAC_F32_e32 %VGPR0<undef>, %VGPR1<kill>, %VGPR7<kill,tied0>, %EXEC<imp-use> %VGPR3_VGPR4_VGPR5_VGPR6<def> = COPY %VGPR0_VGPR1_VGPR2_VGPR3 %VGPR4<def> = COPY %VGPR2 The copy for VGPR1 -> VGPR4 was an error from reading undefined VGPR1, but VGPR4 is defined immediately after this copy. llvm-svn: 275635
2016-07-16 06:32:02 +08:00
%partially.undef.0 = insertelement <4 x i32> undef, i32 %tmp0, i32 0
%partially.undef.1 = insertelement <4 x i32> %partially.undef.0, i32 %tmp1, i32 0
store volatile <4 x i32> %partially.undef.1, <4 x i32> addrspace(1)* undef, align 16
AMDGPU: Use correct register names in inline assembly Fixes using physical registers in inline asm from clang. llvm-svn: 305004
2017-06-09 03:03:20 +08:00
tail call void asm sideeffect "v_nop", "v={v[5:8]}"(<4 x i32> %partially.undef.0)
AMDGPU: Fix verifier error from partially undef copy In this situation: %VGPR2<def> = BUFFER_LOAD_DWORD_OFFSET %SGPR8_SGPR9_SGPR10_SGPR11, %VGPR7<def,tied3> = V_MAC_F32_e32 %VGPR0<undef>, %VGPR1<kill>, %VGPR7<kill,tied0>, %EXEC<imp-use> %VGPR3_VGPR4_VGPR5_VGPR6<def> = COPY %VGPR0_VGPR1_VGPR2_VGPR3 %VGPR4<def> = COPY %VGPR2 The copy for VGPR1 -> VGPR4 was an error from reading undefined VGPR1, but VGPR4 is defined immediately after this copy. llvm-svn: 275635
2016-07-16 06:32:02 +08:00
ret void
}
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) #1
AMDGPU: Fix verifier error from partially undef copy In this situation: %VGPR2<def> = BUFFER_LOAD_DWORD_OFFSET %SGPR8_SGPR9_SGPR10_SGPR11, %VGPR7<def,tied3> = V_MAC_F32_e32 %VGPR0<undef>, %VGPR1<kill>, %VGPR7<kill,tied0>, %EXEC<imp-use> %VGPR3_VGPR4_VGPR5_VGPR6<def> = COPY %VGPR0_VGPR1_VGPR2_VGPR3 %VGPR4<def> = COPY %VGPR2 The copy for VGPR1 -> VGPR4 was an error from reading undefined VGPR1, but VGPR4 is defined immediately after this copy. llvm-svn: 275635
2016-07-16 06:32:02 +08:00
attributes #0 = { nounwind }
AMDGPU: Convert image intrinsic uses in tests llvm-svn: 298386
2017-03-22 00:24:12 +08:00
attributes #1 = { nounwind readonly }