[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)
Shilei Tian via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Thu Oct 31 11:05:48 PDT 2024
https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438
>From 66264a1254c322fc0d3aa464125370886ad7da7c Mon Sep 17 00:00:00 2001
From: Shilei Tian <i at tianshilei.me>
Date: Thu, 31 Oct 2024 12:49:07 -0400
Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor
existing attribute
---
llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp | 80 +++++++++++--------
.../CodeGen/AMDGPU/propagate-waves-per-eu.ll | 47 ++++++-----
2 files changed, 69 insertions(+), 58 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
index 205673cdcc0e23..9a165d9be529e2 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
@@ -215,6 +215,19 @@ class AMDGPUInformationCache : public InformationCache {
return ST.getWavesPerEU(F, FlatWorkGroupSize);
}
+ std::optional<std::pair<unsigned, unsigned>>
+ getWavesPerEUAttr(const Function &F) {
+ Attribute Attr = F.getFnAttribute("amdgpu-waves-per-eu");
+ if (!Attr.isStringAttribute())
+ return std::nullopt;
+ auto Val = parseRangeAttribute(Attr.getValueAsString());
+ if (Val && Val->second == 0) {
+ const GCNSubtarget &ST = TM.getSubtarget<GCNSubtarget>(F);
+ Val->second = ST.getMaxWavesPerEU();
+ }
+ return Val;
+ }
+
std::pair<unsigned, unsigned>
getEffectiveWavesPerEU(const Function &F,
std::pair<unsigned, unsigned> WavesPerEU,
@@ -785,22 +798,6 @@ struct AAAMDSizeRangeAttribute
/*ForceReplace=*/true);
}
- ChangeStatus emitAttributeIfNotDefault(Attributor &A, unsigned Min,
- unsigned Max) {
- // Don't add the attribute if it's the implied default.
- if (getAssumed().getLower() == Min && getAssumed().getUpper() - 1 == Max)
- return ChangeStatus::UNCHANGED;
-
- Function *F = getAssociatedFunction();
- LLVMContext &Ctx = F->getContext();
- SmallString<10> Buffer;
- raw_svector_ostream OS(Buffer);
- OS << getAssumed().getLower() << ',' << getAssumed().getUpper() - 1;
- return A.manifestAttrs(getIRPosition(),
- {Attribute::get(Ctx, AttrName, OS.str())},
- /*ForceReplace=*/true);
- }
-
const std::string getAsStr(Attributor *) const override {
std::string Str;
raw_string_ostream OS(Str);
@@ -885,29 +882,44 @@ struct AAAMDWavesPerEU : public AAAMDSizeRangeAttribute {
AAAMDWavesPerEU(const IRPosition &IRP, Attributor &A)
: AAAMDSizeRangeAttribute(IRP, A, "amdgpu-waves-per-eu") {}
- bool isValidState() const override {
- return !Assumed.isEmptySet() && IntegerRangeState::isValidState();
- }
-
void initialize(Attributor &A) override {
Function *F = getAssociatedFunction();
auto &InfoCache = static_cast<AMDGPUInformationCache &>(A.getInfoCache());
- if (const auto *AssumedGroupSize = A.getAAFor<AAAMDFlatWorkGroupSize>(
- *this, IRPosition::function(*F), DepClassTy::REQUIRED);
- AssumedGroupSize->isValidState()) {
-
- unsigned Min, Max;
- std::tie(Min, Max) = InfoCache.getWavesPerEU(
- *F, {AssumedGroupSize->getAssumed().getLower().getZExtValue(),
- AssumedGroupSize->getAssumed().getUpper().getZExtValue() - 1});
-
+ auto TakeRange = [&](std::pair<unsigned, unsigned> R) {
+ auto [Min, Max] = R;
ConstantRange Range(APInt(32, Min), APInt(32, Max + 1));
- intersectKnown(Range);
+ IntegerRangeState RangeState(Range);
+ clampStateAndIndicateChange(this->getState(), RangeState);
+ indicateOptimisticFixpoint();
+ };
+
+ // If the attribute exists, simple honor it.
+ if (auto Attr = InfoCache.getWavesPerEUAttr(*F)) {
+ TakeRange(*Attr);
+ return;
}
- if (AMDGPU::isEntryFunctionCC(F->getCallingConv()))
- indicatePessimisticFixpoint();
+ // It's getting trickier here, different from AAAMDFlatWorkGroupSize. Since
+ // the calculation of waves per EU involves flat work group size, we can't
+ // simply use an assumed flat work group size as a start point, because the
+ // update of flat work group size is in an inverse direction of waves per
+ // EU. However, we can still do something if it is an entry function. Since
+ // an entry function is a terminal node, and flat work group size either
+ // from attribute or default will be used anyway, we can take that value and
+ // calculate the waves per EU based on it. This result can't be updated by
+ // no means, but that could still allow us to propagate it.
+ if (AMDGPU::isEntryFunctionCC(F->getCallingConv())) {
+ std::pair<unsigned, unsigned> MaxWavesPerEURange{
+ 1U, InfoCache.getMaxWavesPerEU(*F)};
+ std::pair<unsigned, unsigned> FlatWorkGroupSize;
+ if (auto Attr = InfoCache.getFlatWorkGroupSizeAttr(*F))
+ FlatWorkGroupSize = *Attr;
+ else
+ FlatWorkGroupSize = InfoCache.getDefaultFlatWorkGroupSize(*F);
+ TakeRange(InfoCache.getEffectiveWavesPerEU(*F, MaxWavesPerEURange,
+ FlatWorkGroupSize));
+ }
}
ChangeStatus updateImpl(Attributor &A) override {
@@ -956,8 +968,8 @@ struct AAAMDWavesPerEU : public AAAMDSizeRangeAttribute {
ChangeStatus manifest(Attributor &A) override {
Function *F = getAssociatedFunction();
auto &InfoCache = static_cast<AMDGPUInformationCache &>(A.getInfoCache());
- unsigned Max = InfoCache.getMaxWavesPerEU(*F);
- return emitAttributeIfNotDefault(A, 1, Max);
+ return emitAttributeIfNotDefaultAfterClamp(
+ A, {1U, InfoCache.getMaxWavesPerEU(*F)});
}
/// See AbstractAttribute::getName()
diff --git a/llvm/test/CodeGen/AMDGPU/propagate-waves-per-eu.ll b/llvm/test/CodeGen/AMDGPU/propagate-waves-per-eu.ll
index 1272bf655e309d..e28bccfb99343b 100644
--- a/llvm/test/CodeGen/AMDGPU/propagate-waves-per-eu.ll
+++ b/llvm/test/CodeGen/AMDGPU/propagate-waves-per-eu.ll
@@ -117,7 +117,7 @@ define amdgpu_kernel void @kernel_2_9() #6 {
define amdgpu_kernel void @kernel_9_9() #7 {
; CHECK-LABEL: define amdgpu_kernel void @kernel_9_9
-; CHECK-SAME: () #[[ATTR6]] {
+; CHECK-SAME: () #[[ATTR8:[0-9]+]] {
; CHECK-NEXT: call void @default_to_2_9()
; CHECK-NEXT: call void @flat_group_9_10()
; CHECK-NEXT: ret void
@@ -140,7 +140,7 @@ define internal void @default_to_1_8_b() {
; this should probably be illegal.
define amdgpu_kernel void @kernel_2_8() #4 {
; CHECK-LABEL: define amdgpu_kernel void @kernel_2_8
-; CHECK-SAME: () #[[ATTR8:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR5]] {
; CHECK-NEXT: call void @default_to_1_8_a()
; CHECK-NEXT: call void @default_to_1_8_b()
; CHECK-NEXT: ret void
@@ -153,7 +153,7 @@ define amdgpu_kernel void @kernel_2_8() #4 {
; 1,2 -> 2,2
define internal void @merge_cycle_0() #1 {
; CHECK-LABEL: define internal void @merge_cycle_0
-; CHECK-SAME: () #[[ATTR5]] {
+; CHECK-SAME: () #[[ATTR2]] {
; CHECK-NEXT: call void @merge_cycle_1()
; CHECK-NEXT: ret void
;
@@ -165,7 +165,7 @@ define internal void @merge_cycle_0() #1 {
; 2,8 -> 2,8
define internal void @merge_cycle_1() #4 {
; CHECK-LABEL: define internal void @merge_cycle_1
-; CHECK-SAME: () #[[ATTR8]] {
+; CHECK-SAME: () #[[ATTR5]] {
; CHECK-NEXT: call void @merge_cycle_0()
; CHECK-NEXT: ret void
;
@@ -235,7 +235,7 @@ define internal void @called_from_invalid_bounds_1() {
; Invalid range for amdgpu-waves-per-eu
define amdgpu_kernel void @kernel_invalid_bounds_0_8() #9 {
; CHECK-LABEL: define amdgpu_kernel void @kernel_invalid_bounds_0_8
-; CHECK-SAME: () #[[ATTR11:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR1]] {
; CHECK-NEXT: call void @called_from_invalid_bounds_0()
; CHECK-NEXT: ret void
;
@@ -246,7 +246,7 @@ define amdgpu_kernel void @kernel_invalid_bounds_0_8() #9 {
; Invalid range for amdgpu-waves-per-eu
define amdgpu_kernel void @kernel_invalid_bounds_1_123() #10 {
; CHECK-LABEL: define amdgpu_kernel void @kernel_invalid_bounds_1_123
-; CHECK-SAME: () #[[ATTR12:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR11:[0-9]+]] {
; CHECK-NEXT: call void @called_from_invalid_bounds_1()
; CHECK-NEXT: ret void
;
@@ -260,7 +260,7 @@ define amdgpu_kernel void @kernel_invalid_bounds_1_123() #10 {
; -> 2,10
define void @larger_group_size_implies_lower_minimum() #11 {
; CHECK-LABEL: define void @larger_group_size_implies_lower_minimum
-; CHECK-SAME: () #[[ATTR13:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR12:[0-9]+]] {
; CHECK-NEXT: ret void
;
ret void
@@ -268,7 +268,7 @@ define void @larger_group_size_implies_lower_minimum() #11 {
define amdgpu_kernel void @kernel_3_6() #12 {
; CHECK-LABEL: define amdgpu_kernel void @kernel_3_6
-; CHECK-SAME: () #[[ATTR14:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR13:[0-9]+]] {
; CHECK-NEXT: call void @larger_group_size_implies_lower_minimum()
; CHECK-NEXT: ret void
;
@@ -279,7 +279,7 @@ define amdgpu_kernel void @kernel_3_6() #12 {
; 3,6 -> 6,9
define internal void @refine_upper_func_3_6() #13 {
; CHECK-LABEL: define internal void @refine_upper_func_3_6
-; CHECK-SAME: () #[[ATTR15:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR14:[0-9]+]] {
; CHECK-NEXT: ret void
;
ret void
@@ -288,7 +288,7 @@ define internal void @refine_upper_func_3_6() #13 {
; 4,8 -> 6,8
define internal void @refine_lower_func_4_8() #14 {
; CHECK-LABEL: define internal void @refine_lower_func_4_8
-; CHECK-SAME: () #[[ATTR16:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR15:[0-9]+]] {
; CHECK-NEXT: call void @refine_upper_func_3_6()
; CHECK-NEXT: ret void
;
@@ -298,7 +298,7 @@ define internal void @refine_lower_func_4_8() #14 {
define amdgpu_kernel void @kernel_foo_6_8() #15 {
; CHECK-LABEL: define amdgpu_kernel void @kernel_foo_6_8
-; CHECK-SAME: () #[[ATTR16]] {
+; CHECK-SAME: () #[[ATTR16:[0-9]+]] {
; CHECK-NEXT: call void @refine_upper_func_3_6()
; CHECK-NEXT: call void @refine_lower_func_4_8()
; CHECK-NEXT: call void @func_9_10_a()
@@ -340,7 +340,7 @@ define internal void @func_9_10_a() #18 {
; 9,10 -> 9,9
define internal void @func_9_10_b() #18 {
; CHECK-LABEL: define internal void @func_9_10_b
-; CHECK-SAME: () #[[ATTR20:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR19]] {
; CHECK-NEXT: ret void
;
ret void
@@ -348,7 +348,7 @@ define internal void @func_9_10_b() #18 {
define amdgpu_kernel void @kernel_bar_8_9() #19 {
; CHECK-LABEL: define amdgpu_kernel void @kernel_bar_8_9
-; CHECK-SAME: () #[[ATTR21:[0-9]+]] {
+; CHECK-SAME: () #[[ATTR20:[0-9]+]] {
; CHECK-NEXT: call void @refine_upper_func_3_6()
; CHECK-NEXT: call void @func_5_5()
; CHECK-NEXT: call void @func_9_10_b()
@@ -404,21 +404,20 @@ attributes #19 = { "amdgpu-waves-per-eu"="8,9" }
; CHECK: attributes #[[ATTR2]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="1,2" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR3]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="1,4" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR4]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="1,1" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR5]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="2,2" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR6]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="9,9" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR5]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="2,8" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR6]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="9,10" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR7]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="2,9" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR8]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="2,8" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR8]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="9,9" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR9]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="3,8" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR10]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR11]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="0,8" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR12]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="1,123" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR13]] = { "amdgpu-flat-work-group-size"="1,512" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="2,10" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR14]] = { "amdgpu-flat-work-group-size"="1,512" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="3,6" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR15]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="6,9" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR11]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="1,123" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR12]] = { "amdgpu-flat-work-group-size"="1,512" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR13]] = { "amdgpu-flat-work-group-size"="1,512" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="3,6" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR14]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="3,6" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR15]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="4,8" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR16]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="6,8" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR17]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="5,5" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR18]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="8,8" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR18]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="5,8" "uniform-work-group-size"="false" }
; CHECK: attributes #[[ATTR19]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="9,10" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR20]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="9,9" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR21]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="8,9" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR20]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "amdgpu-waves-per-eu"="8,9" "uniform-work-group-size"="false" }
;.
More information about the llvm-branch-commits
mailing list