[llvm] [AMDGPU][GlobalISel] Update tests to check for COV5 (PR #76257)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Dec 22 10:19:39 PST 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Saiyedul Islam (saiislam)
<details>
<summary>Changes</summary>
Update GlobalISel tests to assume ABI to be code object version 5.
---
Patch is 851.96 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/76257.diff
18 Files Affected:
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/crash-stack-address-O0.ll (+4-1)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll (+44-44)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll (+11-8)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-atomicrmw.ll (+5-2)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll (+56-55)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-implicit-args.ll (+470-484)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-return-values.ll (+1581-1623)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-sret.ll (+34-32)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll (+2015-2076)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-constant-fold-vector-op.ll (+5-2)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-indirect-call.ll (+34-32)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-inline-asm.ll (+59-57)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-sibling-call.ll (+21-18)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-tail-call.ll (+5-2)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.is.private.ll (+8-6)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.is.shared.ll (+8-6)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/non-entry-alloca.ll (+10-4)
- (modified) llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll (+13-6)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/crash-stack-address-O0.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/crash-stack-address-O0.ll
index 0df80d67e77157..9580326d7b78fa 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/crash-stack-address-O0.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/crash-stack-address-O0.ll
@@ -7,7 +7,7 @@
define amdgpu_kernel void @stack_write_fi() {
; CHECK-LABEL: stack_write_fi:
; CHECK: ; %bb.0: ; %entry
-; CHECK-NEXT: s_add_u32 s0, s0, s17
+; CHECK-NEXT: s_add_u32 s0, s0, s15
; CHECK-NEXT: s_addc_u32 s1, s1, 0
; CHECK-NEXT: s_mov_b32 s5, 0
; CHECK-NEXT: s_mov_b32 s4, 0
@@ -23,3 +23,6 @@ entry:
store volatile i64 0, ptr addrspace(5) %alloca, align 4
ret void
}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 500}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll
index c4e383c3708b33..44c4910bac7ea1 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll
@@ -7,48 +7,47 @@ declare void @callee()
define amdgpu_kernel void @call_debug_loc() {
; CHECK-LABEL: name: call_debug_loc
; CHECK: bb.1.entry:
- ; CHECK-NEXT: liveins: $sgpr14, $sgpr15, $sgpr16, $vgpr0, $vgpr1, $vgpr2, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: liveins: $sgpr12, $sgpr13, $sgpr14, $vgpr0, $vgpr1, $vgpr2, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2, debug-location !6
- ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1, debug-location !6
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0, debug-location !6
- ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr16, debug-location !6
- ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr15, debug-location !6
- ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr14, debug-location !6
- ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11, debug-location !6
- ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7, debug-location !6
- ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5, debug-location !6
- ; CHECK-NEXT: [[COPY9:%[0-9]+]]:sreg_64 = COPY $sgpr8_sgpr9
- ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, debug-location !6
- ; CHECK-NEXT: [[COPY10:%[0-9]+]]:sreg_64 = COPY [[COPY8]], debug-location !6
- ; CHECK-NEXT: [[COPY11:%[0-9]+]]:sreg_64 = COPY [[COPY7]], debug-location !6
- ; CHECK-NEXT: [[COPY12:%[0-9]+]]:sreg_64 = COPY [[COPY6]], debug-location !6
- ; CHECK-NEXT: [[COPY13:%[0-9]+]]:sreg_32 = COPY [[COPY5]], debug-location !6
- ; CHECK-NEXT: [[COPY14:%[0-9]+]]:sreg_32 = COPY [[COPY4]], debug-location !6
- ; CHECK-NEXT: [[COPY15:%[0-9]+]]:sreg_32 = COPY [[COPY3]], debug-location !6
- ; CHECK-NEXT: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF debug-location !6
- ; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 10, debug-location !6
- ; CHECK-NEXT: [[COPY16:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]], debug-location !6
- ; CHECK-NEXT: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY16]], [[COPY1]], implicit $exec, debug-location !6
- ; CHECK-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 20, debug-location !6
- ; CHECK-NEXT: [[COPY17:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]], debug-location !6
- ; CHECK-NEXT: [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY17]], [[COPY]], implicit $exec, debug-location !6
- ; CHECK-NEXT: [[V_OR3_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR3_B32_e64 [[COPY2]], [[V_LSHLREV_B32_e64_]], [[V_LSHLREV_B32_e64_1]], implicit $exec, debug-location !6
- ; CHECK-NEXT: [[COPY18:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3, debug-location !6
- ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY18]], debug-location !6
- ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY10]], debug-location !6
- ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY11]], debug-location !6
- ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY9]], debug-location !6
- ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY12]], debug-location !6
- ; CHECK-NEXT: $sgpr12 = COPY [[COPY13]], debug-location !6
- ; CHECK-NEXT: $sgpr13 = COPY [[COPY14]], debug-location !6
- ; CHECK-NEXT: $sgpr14 = COPY [[COPY15]], debug-location !6
- ; CHECK-NEXT: $sgpr15 = COPY [[DEF]], debug-location !6
- ; CHECK-NEXT: $vgpr31 = COPY [[V_OR3_B32_e64_]], debug-location !6
- ; CHECK-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee, target-flags(amdgpu-gotprel32-hi) @callee, implicit-def $scc, debug-location !6
- ; CHECK-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0, debug-location !6 :: (dereferenceable invariant load (p0) from got, addrspace 4)
- ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent SI_CALL [[S_LOAD_DWORDX2_IMM]], @callee, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31, debug-location !6
- ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, debug-location !6
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2, debug-location !7
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1, debug-location !7
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0, debug-location !7
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr14, debug-location !7
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr13, debug-location !7
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr12, debug-location !7
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9, debug-location !7
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5, debug-location !7
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:sreg_64 = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, debug-location !7
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:sreg_64 = COPY [[COPY7]], debug-location !7
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF debug-location !7
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:sreg_64 = COPY [[COPY6]], debug-location !7
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:sreg_32 = COPY [[COPY5]], debug-location !7
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:sreg_32 = COPY [[COPY4]], debug-location !7
+ ; CHECK-NEXT: [[COPY13:%[0-9]+]]:sreg_32 = COPY [[COPY3]], debug-location !7
+ ; CHECK-NEXT: [[DEF1:%[0-9]+]]:sreg_32 = IMPLICIT_DEF debug-location !7
+ ; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 10, debug-location !7
+ ; CHECK-NEXT: [[COPY14:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]], debug-location !7
+ ; CHECK-NEXT: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY14]], [[COPY1]], implicit $exec, debug-location !7
+ ; CHECK-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 20, debug-location !7
+ ; CHECK-NEXT: [[COPY15:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]], debug-location !7
+ ; CHECK-NEXT: [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY15]], [[COPY]], implicit $exec, debug-location !7
+ ; CHECK-NEXT: [[V_OR3_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR3_B32_e64 [[COPY2]], [[V_LSHLREV_B32_e64_]], [[V_LSHLREV_B32_e64_1]], implicit $exec, debug-location !7
+ ; CHECK-NEXT: [[COPY16:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3, debug-location !7
+ ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY16]], debug-location !7
+ ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY9]], debug-location !7
+ ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[DEF]], debug-location !7
+ ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY8]], debug-location !7
+ ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY10]], debug-location !7
+ ; CHECK-NEXT: $sgpr12 = COPY [[COPY11]], debug-location !7
+ ; CHECK-NEXT: $sgpr13 = COPY [[COPY12]], debug-location !7
+ ; CHECK-NEXT: $sgpr14 = COPY [[COPY13]], debug-location !7
+ ; CHECK-NEXT: $sgpr15 = COPY [[DEF1]], debug-location !7
+ ; CHECK-NEXT: $vgpr31 = COPY [[V_OR3_B32_e64_]], debug-location !7
+ ; CHECK-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee, target-flags(amdgpu-gotprel32-hi) @callee, implicit-def $scc, debug-location !7
+ ; CHECK-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0, debug-location !7 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+ ; CHECK-NEXT: $sgpr30_sgpr31 = noconvergent SI_CALL [[S_LOAD_DWORDX2_IMM]], @callee, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31, debug-location !7
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, debug-location !7
; CHECK-NEXT: S_ENDPGM 0
entry:
call void @callee(), !dbg !6
@@ -60,11 +59,11 @@ define void @returnaddress_debug_loc(ptr addrspace(1) %ptr) {
; CHECK: bb.1.entry:
; CHECK-NEXT: liveins: $vgpr0, $vgpr1, $sgpr30_sgpr31
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr30_sgpr31, debug-location !6
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr30_sgpr31, debug-location !7
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1
- ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[COPY]], debug-location !6
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[COPY]], debug-location !7
; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[REG_SEQUENCE]], [[COPY3]], 0, 0, implicit $exec :: (store (p0) into %ir.ptr, addrspace 1)
; CHECK-NEXT: SI_RETURN
entry:
@@ -78,7 +77,7 @@ declare ptr @llvm.returnaddress(i32 immarg) #0
attributes #0 = { nofree nosync nounwind readnone willreturn }
!llvm.dbg.cu = !{!0}
-!llvm.module.flags = !{!2, !3, !4, !5}
+!llvm.module.flags = !{!2, !3, !4, !5, !10}
!0 = distinct !DICompileUnit(language: DW_LANG_OpenCL, file: !1, producer: "clang version 14.0.0 (git at github.com:llvm/llvm-project.git 4132dc917eddb446405cc5afef41167b8bce360b)", isOptimized: false, runtimeVersion: 0, emissionKind: NoDebug, splitDebugInlining: false, nameTableKind: None)
!1 = !DIFile(filename: "gisel_1_gfx1031.cl", directory: "/home/matt/builds/conformance/2.0")
@@ -90,3 +89,4 @@ attributes #0 = { nofree nosync nounwind readnone willreturn }
!7 = distinct !DISubprogram(name: "call_debug_loc", scope: !1, file: !1, line: 8, type: !8, scopeLine: 9, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition, unit: !0, retainedNodes: !9)
!8 = !DISubroutineType(types: !9)
!9 = !{}
+!10 = !{i32 1, !"amdgpu_code_object_version", i32 500}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll
index a2f1308fdbedd8..83c331c5573c99 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll
@@ -32,13 +32,13 @@ define void @call_result_align_1() {
; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
- ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
; CHECK-NEXT: [[C:%[0-9]+]]:_(s8) = G_CONSTANT i8 0
; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @returns_ptr
; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(p4) = COPY [[COPY8]]
- ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]]
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY6]]
; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(s64) = COPY [[COPY5]]
; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s32) = COPY [[COPY4]]
@@ -81,13 +81,13 @@ define void @call_result_align_8() {
; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
- ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
; CHECK-NEXT: [[C:%[0-9]+]]:_(s8) = G_CONSTANT i8 0
; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @returns_ptr
; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(p4) = COPY [[COPY8]]
- ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]]
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY6]]
; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(s64) = COPY [[COPY5]]
; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s32) = COPY [[COPY4]]
@@ -131,13 +131,13 @@ define void @declaration_result_align_8() {
; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
- ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
; CHECK-NEXT: [[C:%[0-9]+]]:_(s8) = G_CONSTANT i8 0
; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @returns_ptr_align8
; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(p4) = COPY [[COPY8]]
- ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]]
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY6]]
; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(s64) = COPY [[COPY5]]
; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s32) = COPY [[COPY4]]
@@ -181,11 +181,11 @@ define ptr addrspace(1) @tail_call_assert_align() {
; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr12
; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
; CHECK-NEXT: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
- ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:sgpr_64(p4) = COPY $sgpr6_sgpr7
; CHECK-NEXT: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
; CHECK-NEXT: [[GV:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @returns_ptr_align8
; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(p4) = COPY [[COPY8]]
- ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]]
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(p4) = COPY [[COPY7]](p4)
; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(p4) = COPY [[COPY6]]
; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(s64) = COPY [[COPY5]]
; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s32) = COPY [[COPY4]]
@@ -209,3 +209,6 @@ entry:
%call = tail call ptr addrspace(1) @returns_ptr_align8()
ret ptr addrspace(1) %call
}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 500}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-atomicrmw.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-atomicrmw.ll
index 9359bde339bb42..8069698526bf08 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-atomicrmw.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-atomicrmw.ll
@@ -30,8 +30,8 @@ define float @test_atomicrmw_fsub(ptr addrspace(3) %addr) {
; CHECK-NEXT: bb.2.atomicrmw.start:
; CHECK-NEXT: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: [[PHI:%[0-9]+]]:_(s64) = G_PHI %16(s64), %bb.2, [[C1]](s64), %bb.1
- ; CHECK-NEXT: [[PHI1:%[0-9]+]]:_(s32) = G_PHI [[LOAD]](s32), %bb.1, %14(s32), %bb.2
+ ; CHECK-NEXT: [[PHI:%[0-9]+]]:_(s64) = G_PHI %15(s64), %bb.2, [[C1]](s64), %bb.1
+ ; CHECK-NEXT: [[PHI1:%[0-9]+]]:_(s32) = G_PHI [[LOAD]](s32), %bb.1, %13(s32), %bb.2
; CHECK-NEXT: [[FSUB:%[0-9]+]]:_(s32) = G_FSUB [[PHI1]], [[C]]
; CHECK-NEXT: [[ATOMIC_CMPXCHG_WITH_SUCCESS:%[0-9]+]]:_(s32), [[ATOMIC_CMPXCHG_WITH_SUCCESS1:%[0-9]+]]:_(s1) = G_ATOMIC_CMPXCHG_WITH_SUCCESS [[COPY]](p3), [[PHI1]], [[FSUB]] :: (load store seq_cst seq_cst (s32) on %ir.addr, addrspace 3)
; CHECK-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s64) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.if.break), [[ATOMIC_CMPXCHG_WITH_SUCCESS1]](s1), [[PHI]](s64)
@@ -48,3 +48,6 @@ define float @test_atomicrmw_fsub(ptr addrspace(3) %addr) {
%oldval = atomicrmw fsub ptr addrspace(3) %addr, float 1.0 seq_cst
ret float %oldval
}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 500}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll
index 4cf02c935f1b01..ca889de30c6500 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll
@@ -9,37 +9,36 @@ declare hidden void @extern()
define amdgpu_kernel void @kernel_call_no_workitem_ids() {
; CHECK-LABEL: name: kernel_call_no_workitem_ids
; CHECK: bb.1 (%ir-block.0):
- ; CHECK-NEXT: liveins: $sgpr14, $sgpr15, $sgpr16, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
+ ; CHECK-NEXT: liveins: $sgpr12, $sgpr13, $sgpr14, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr16
- ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr15
- ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr14
- ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11
- ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7
- ; CHECK-NEXT: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
- ; CHECK-NEXT: [[COPY6:%[0-9]+]]:_(p4) = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr14
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr13
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr12
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:sgpr_64 = COPY $sgpr8_sgpr9
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:_(p4) = COPY $sgpr6_sgpr7
; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc
; CHECK-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @extern
- ; CHECK-NEXT: [[COPY7:%[0-9]+]]:_(p4) = COPY [[COPY5]]
- ; CHECK-NEXT: [[COPY8:%[0-9]+]]:_(p4) = COPY [[COPY4]]
- ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(p4) = COPY [[COPY6]](p4)
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:_(p4) = COPY [[COPY4]]
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(p4) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[COPY7:%[0-9]+]]:_(p4) = COPY [[COPY5]](p4)
; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
- ; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p4) = G_PTR_ADD [[COPY9]], [[C]](s64)
- ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s64) = COPY [[COPY3]]
- ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(s32) = COPY [[COPY2]]
- ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(s32) = COPY [[COPY1]]
- ; CHECK-NEXT: [[COPY13:%[0-9]+]]:_(s32) = COPY [[COPY]]
- ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
- ; CHECK-NEXT: [[COPY14:%[0-9]+]]:_(<4 x s32>) = COPY $private_rsrc_reg
- ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY14]](<4 x s32>)
- ; CHECK-NEXT: $sgpr4_sgpr5 = COPY [[COPY7]](p4)
- ; CHECK-NEXT: $sgpr6_sgpr7 = COPY [[COPY8]](p4)
+ ; CHECK-NEXT: [[PTR_ADD:%[0-9]+]]:_(p4) = G_PTR_ADD [[COPY7]], [[C]](s64)
+ ; CHECK-NEXT: [[COPY8:%[0-9]+]]:_(s64) = COPY [[COPY3]]
+ ; CHECK-NEXT: [[COPY9:%[0-9]+]]:_(s32) = COPY [[COPY2]]
+ ; CHECK-NEXT: [[COPY10:%[0-9]+]]:_(s32) = COPY [[COPY1]]
+ ; CHECK-NEXT: [[COPY11:%[0-9]+]]:_(s32) = COPY [[COPY]]
+ ; CHECK-NEXT: [[DEF1:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
+ ; CHECK-NEXT: [[COPY12:%[0-9]+]]:_(<4 x s32>) = COPY $private_rsrc_reg
+ ; CHEC...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/76257
More information about the llvm-commits
mailing list