summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/memory_clause.mir
diff options
context:
space:
mode:
authorStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>2018-05-31 20:13:51 +0000
committerStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>2018-05-31 20:13:51 +0000
commit739174c4be36d13a22bad1187e444f4a804db407 (patch)
tree07ca122e021d1251fe1d3409d014eae96f25bcf1 /llvm/test/CodeGen/AMDGPU/memory_clause.mir
parenta6922415b163a46a860c93d4d4e042320363e7c7 (diff)
downloadbcm5719-llvm-739174c4be36d13a22bad1187e444f4a804db407.tar.gz
bcm5719-llvm-739174c4be36d13a22bad1187e444f4a804db407.zip
[AMDGPU] Construct memory clauses before RA
Memory clauses are formed into bundles in presence of xnack. Their source operands are marked as early-clobber. This allows to allocate distinct source and destination registers within a clause and prevent breaking the clause with s_nop in the hazard recognizer. Clauses are undone before post-RA scheduler to allow some rescheduling, which will not break the clause since artificial edges are created in the dag to keep memory operations together. Yet this allows a better ILP in some cases. Differential Revision: https://reviews.llvm.org/D47511 llvm-svn: 333691
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/memory_clause.mir')
-rw-r--r--llvm/test/CodeGen/AMDGPU/memory_clause.mir388
1 files changed, 388 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/memory_clause.mir b/llvm/test/CodeGen/AMDGPU/memory_clause.mir
new file mode 100644
index 00000000000..4a40a3324db
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/memory_clause.mir
@@ -0,0 +1,388 @@
+# RUN: llc -march=amdgcn -mcpu=gfx902 -verify-machineinstrs -run-pass=phi-node-elimination,si-form-memory-clauses %s -o - | FileCheck -check-prefix=GCN %s
+
+# GCN-LABEL: {{^}}name: vector_clause{{$}}
+# GCN: early-clobber %2:vreg_128, early-clobber %4:vreg_128, early-clobber %1:vreg_128, early-clobber %3:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+# GCN-NEXT: %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+# GCN-NEXT: %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+
+---
+name: vector_clause
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vreg_128 }
+ - { id: 2, class: vreg_128 }
+ - { id: 3, class: vreg_128 }
+ - { id: 4, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+ %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+ %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+ %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %2, 16, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %3, 32, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %4, 48, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: subreg_full{{$}}
+# GCN: early-clobber %1:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+# GCN-NEXT: internal %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+# GCN-NEXT: internal %1.sub2:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+# GCN-NEXT: internal %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+
+---
+name: subreg_full
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_128 }
+ - { id: 1, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+ %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+ %1.sub2:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+ %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: subreg_part{{$}}
+# GCN: undef early-clobber %1.sub0_sub1:vreg_128, undef early-clobber %1.sub3:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+# GCN-NEXT: internal %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+# GCN-NEXT: internal %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+
+---
+name: subreg_part
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_128 }
+ - { id: 1, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, 0, implicit $exec
+ %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, 0, implicit $exec
+ %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: dead{{$}}
+# GCN: dead early-clobber %2:vreg_128, dead early-clobber %4:vreg_128, dead early-clobber %1:vreg_128, dead early-clobber %3:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name: dead
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vreg_128 }
+ - { id: 2, class: vreg_128 }
+ - { id: 3, class: vreg_128 }
+ - { id: 4, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+ dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+ dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+ dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: subreg_dead{{$}}
+# GCN: early-clobber %1:vreg_64 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: %1.sub0:vreg_64 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+# GCN-NEXT: dead %1.sub1:vreg_64 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: GLOBAL_STORE_DWORD %0, %1.sub0, 0, 0, 0, implicit $exec
+
+---
+name: subreg_dead
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vreg_64 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ undef %1.sub0:vreg_64 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+ dead %1.sub1:vreg_64 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORD %0, %1.sub0, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: kill{{$}}
+# GCN: early-clobber %2:vreg_128, early-clobber %3:vreg_128 = BUNDLE %0, %1, implicit $exec {
+# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT: %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name: kill
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vreg_64 }
+ - { id: 2, class: vreg_128 }
+ - { id: 3, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1 = IMPLICIT_DEF
+ %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+ %3:vreg_128 = GLOBAL_LOAD_DWORDX4 killed %1, 16, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %2, 0, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %3, 16, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: indirect{{$}}
+# GCN: %1:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT: early-clobber %2:vreg_128, early-clobber %3:vreg_128 = BUNDLE %1, implicit $exec {
+# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 0, 0, 0, implicit $exec
+# GCN-NEXT: %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name: indirect
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vreg_64 }
+ - { id: 2, class: vreg_128 }
+ - { id: 3, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, 0, implicit $exec
+ %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 0, 0, 0, implicit $exec
+ %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %2, 0, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %3, 16, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: stack{{$}}
+# GCN: %0:vreg_64 = IMPLICIT_DEF
+# GCN-NEXT: %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 0, 0, 0, implicit $exec
+# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 16, 0, 0, implicit $exec
+# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+
+---
+name: stack
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vreg_128 }
+ - { id: 2, class: vreg_128 }
+stack:
+ - { id: 0, type: default, offset: 0, size: 64, alignment: 8 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 0, 0, 0, implicit $exec
+ %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 16, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, 0, implicit $exec
+ GLOBAL_STORE_DWORDX4 %0, %2, 16, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: overflow_counter{{$}}
+# GCN: dead early-clobber %7:vgpr_32, dead early-clobber %14:vgpr_32, dead early-clobber %2:vgpr_32, dead early-clobber %9:vgpr_32, dead early-clobber %4:vgpr_32, dead early-clobber %11:vgpr_32, dead early-clobber %6:vgpr_32, dead early-clobber %13:vgpr_32, dead early-clobber %1:vgpr_32, dead early-clobber %8:vgpr_32, dead early-clobber %15:vgpr_32, dead early-clobber %3:vgpr_32, dead early-clobber %10:vgpr_32, dead early-clobber %5:vgpr_32, dead early-clobber %12:vgpr_32 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: dead %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, 0, implicit $exec
+# GCN-NEXT: dead %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, 0, implicit $exec
+# GCN-NEXT: dead %3:vgpr_32 = GLOBAL_LOAD_DWORD %0, 8, 0, 0, implicit $exec
+# GCN-NEXT: dead %4:vgpr_32 = GLOBAL_LOAD_DWORD %0, 12, 0, 0, implicit $exec
+# GCN-NEXT: dead %5:vgpr_32 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+# GCN-NEXT: dead %6:vgpr_32 = GLOBAL_LOAD_DWORD %0, 20, 0, 0, implicit $exec
+# GCN-NEXT: dead %7:vgpr_32 = GLOBAL_LOAD_DWORD %0, 24, 0, 0, implicit $exec
+# GCN-NEXT: dead %8:vgpr_32 = GLOBAL_LOAD_DWORD %0, 28, 0, 0, implicit $exec
+# GCN-NEXT: dead %9:vgpr_32 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+# GCN-NEXT: dead %10:vgpr_32 = GLOBAL_LOAD_DWORD %0, 36, 0, 0, implicit $exec
+# GCN-NEXT: dead %11:vgpr_32 = GLOBAL_LOAD_DWORD %0, 40, 0, 0, implicit $exec
+# GCN-NEXT: dead %12:vgpr_32 = GLOBAL_LOAD_DWORD %0, 44, 0, 0, implicit $exec
+# GCN-NEXT: dead %13:vgpr_32 = GLOBAL_LOAD_DWORD %0, 48, 0, 0, implicit $exec
+# GCN-NEXT: dead %14:vgpr_32 = GLOBAL_LOAD_DWORD %0, 52, 0, 0, implicit $exec
+# GCN-NEXT: dead %15:vgpr_32 = GLOBAL_LOAD_DWORD %0, 56, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: dead early-clobber %16:vgpr_32, dead early-clobber %17:vgpr_32 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: dead %16:vgpr_32 = GLOBAL_LOAD_DWORD %0, 60, 0, 0, implicit $exec
+# GCN-NEXT: dead %17:vgpr_32 = GLOBAL_LOAD_DWORD %0, 64, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name: overflow_counter
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vgpr_32 }
+ - { id: 2, class: vgpr_32 }
+ - { id: 3, class: vgpr_32 }
+ - { id: 4, class: vgpr_32 }
+ - { id: 5, class: vgpr_32 }
+ - { id: 6, class: vgpr_32 }
+ - { id: 7, class: vgpr_32 }
+ - { id: 8, class: vgpr_32 }
+ - { id: 9, class: vgpr_32 }
+ - { id: 10, class: vgpr_32 }
+ - { id: 11, class: vgpr_32 }
+ - { id: 12, class: vgpr_32 }
+ - { id: 13, class: vgpr_32 }
+ - { id: 14, class: vgpr_32 }
+ - { id: 15, class: vgpr_32 }
+ - { id: 16, class: vgpr_32 }
+ - { id: 17, class: vgpr_32 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, 0, implicit $exec
+ %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, 0, implicit $exec
+ %3:vgpr_32 = GLOBAL_LOAD_DWORD %0, 8, 0, 0, implicit $exec
+ %4:vgpr_32 = GLOBAL_LOAD_DWORD %0, 12, 0, 0, implicit $exec
+ %5:vgpr_32 = GLOBAL_LOAD_DWORD %0, 16, 0, 0, implicit $exec
+ %6:vgpr_32 = GLOBAL_LOAD_DWORD %0, 20, 0, 0, implicit $exec
+ %7:vgpr_32 = GLOBAL_LOAD_DWORD %0, 24, 0, 0, implicit $exec
+ %8:vgpr_32 = GLOBAL_LOAD_DWORD %0, 28, 0, 0, implicit $exec
+ %9:vgpr_32 = GLOBAL_LOAD_DWORD %0, 32, 0, 0, implicit $exec
+ %10:vgpr_32 = GLOBAL_LOAD_DWORD %0, 36, 0, 0, implicit $exec
+ %11:vgpr_32 = GLOBAL_LOAD_DWORD %0, 40, 0, 0, implicit $exec
+ %12:vgpr_32 = GLOBAL_LOAD_DWORD %0, 44, 0, 0, implicit $exec
+ %13:vgpr_32 = GLOBAL_LOAD_DWORD %0, 48, 0, 0, implicit $exec
+ %14:vgpr_32 = GLOBAL_LOAD_DWORD %0, 52, 0, 0, implicit $exec
+ %15:vgpr_32 = GLOBAL_LOAD_DWORD %0, 56, 0, 0, implicit $exec
+ %16:vgpr_32 = GLOBAL_LOAD_DWORD %0, 60, 0, 0, implicit $exec
+ %17:vgpr_32 = GLOBAL_LOAD_DWORD %0, 64, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: reg_pressure{{$}}
+# GCN: dead early-clobber %2:vreg_128, dead early-clobber %4:vreg_128, dead early-clobber %1:vreg_128, dead early-clobber %3:vreg_128, dead early-clobber %5:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT: dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+# GCN-NEXT: dead %5:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 64, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: dead early-clobber %7:vreg_128, dead early-clobber %6:vreg_128 = BUNDLE %0, implicit $exec {
+# GCN-NEXT: dead %6:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 80, 0, 0, implicit $exec
+# GCN-NEXT: dead %7:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 96, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name: reg_pressure
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vreg_128 }
+ - { id: 2, class: vreg_128 }
+ - { id: 3, class: vreg_128 }
+ - { id: 4, class: vreg_128 }
+ - { id: 5, class: vreg_128 }
+ - { id: 6, class: vreg_128 }
+ - { id: 7, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+ %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, 0, implicit $exec
+ %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, 0, implicit $exec
+ %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, 0, implicit $exec
+ %5:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 64, 0, 0, implicit $exec
+ %6:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 80, 0, 0, implicit $exec
+ %7:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 96, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: image_clause{{$}}
+# GCN: early-clobber %4:vreg_128, early-clobber %3:vreg_128, early-clobber %5:vreg_128 = BUNDLE %0, undef %2:sreg_128, %1, implicit $exec {
+# GCN-NEXT: %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT: %4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT: %5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT: }
+# GCN-NEXT: IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+
+---
+name: image_clause
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: sreg_256 }
+ - { id: 2, class: sreg_128 }
+ - { id: 3, class: vreg_128 }
+ - { id: 4, class: vreg_128 }
+ - { id: 5, class: vreg_128 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1 = IMPLICIT_DEF
+ %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+ %4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+ %5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sreg_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+ IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+ IMAGE_STORE_V4_V2 %4, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+ IMAGE_STORE_V4_V2 %5, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: mixed_clause{{$}}
+# GCN: dead early-clobber %4:vreg_128, dead early-clobber %3:vreg_128, dead early-clobber %5:vgpr_32 = BUNDLE %0, %2, %1, implicit $exec {
+# GCN-NEXT: dead %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+# GCN-NEXT: dead %5:vgpr_32 = BUFFER_LOAD_DWORD_ADDR64 %0, %2, 0, 0, 0, 0, 0, implicit $exec
+# GCN-NEXT: }
+
+---
+name: mixed_clause
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: sreg_256 }
+ - { id: 2, class: sreg_128 }
+ - { id: 3, class: vreg_128 }
+ - { id: 4, class: vreg_128 }
+ - { id: 5, class: vgpr_32 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1 = IMPLICIT_DEF
+ %2 = IMPLICIT_DEF
+ %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+ %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, implicit $exec
+ %5:vgpr_32 = BUFFER_LOAD_DWORD_ADDR64 %0, %2, 0, 0, 0, 0, 0, implicit $exec
+...
+
+# GCN-LABEL: {{^}}name: atomic{{$}}
+# GCN: %1:vgpr_32 = IMPLICIT_DEF
+# GCN-NEXT: dead %2:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: dead %3:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+# GCN-NEXT: S_ENDPGM
+
+---
+name: atomic
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: vreg_64 }
+ - { id: 1, class: vgpr_32 }
+ - { id: 2, class: vgpr_32 }
+ - { id: 3, class: vgpr_32 }
+body: |
+ bb.0:
+ %0 = IMPLICIT_DEF
+ %1 = IMPLICIT_DEF
+ %2:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+ %3:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+ FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+ FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
+ S_ENDPGM
+...
OpenPOWER on IntegriCloud