Support for inserting profile-directed cache prefetches

Summary:
Support for profile-driven cache prefetching (X86)

This change is part of a larger system, consisting of a cache prefetches recommender, create_llvm_prof (https://github.com/google/autofdo), and LLVM.

A proof of concept recommender is DynamoRIO's cache miss analyzer. It processes memory access traces obtained from a running binary and identifies patterns in cache misses. Based on them, it produces a csv file with recommendations. The expectation is that, by leveraging such recommendations, we can reduce the amount of clock cycles spent waiting for data from memory. A microbenchmark based on the DynamoRIO analyzer is available as a proof of concept: https://goo.gl/6TM2Xp.

The recommender makes prefetch recommendations in terms of:

* the binary offset of an instruction with a memory operand;
* a delta;
* and a type (nta, t0, t1, t2)

meaning: a prefetch of that type should be inserted right before the instrution at that binary offset, and the prefetch should be for an address delta away from the memory address the instruction will access.

For example:

0x400ab2,64,nta

and assuming the instruction at 0x400ab2 is:

movzbl (%rbx,%rdx,1),%edx

means that the recommender determined it would be beneficial for a prefetchnta instruction to be inserted right before this instruction, as such:

prefetchnta 0x40(%rbx,%rdx,1)
movzbl (%rbx, %rdx, 1), %edx

The workflow for prefetch cache instrumentation is as follows (the proof of concept script details these steps as well):

1. build binary, making sure -gmlt -fdebug-info-for-profiling is passed. The latter option will enable the X86DiscriminateMemOps pass, which ensures instructions with memory operands are uniquely identifiable (this causes ~2% size increase in total binary size due to the additional debug information).

2. collect memory traces, run analysis to obtain recommendations (see above-referenced DynamoRIO demo as a proof of concept).

3. use create_llvm_prof to convert recommendations to reference insertion locations in terms of debug info locations.

4. rebuild binary, using the exact same set of arguments used initially, to which -mllvm -prefetch-hints-file=<file> needs to be added, using the afdo file obtained at step 3.

Note that if sample profiling feedback-driven optimization is also desired, that happens before step 1 above. In this case, the sample profile afdo file that was used to produce the binary at step 1 must also be included in step 4.

The data needed by the compiler in order to identify prefetch insertion points is very similar to what is needed for sample profiles. For this reason, and given that the overall approach (memory tracing-based cache recommendation mechanisms) is under active development, we use the afdo format as a syntax for capturing this information. We avoid confusing semantics with sample profile afdo data by feeding the two types of information to the compiler through separate files and compiler flags. Should the approach prove successful, we can investigate improvements to this encoding mechanism.

Reviewers: davidxl, wmi, craig.topper

Reviewed By: davidxl, wmi, craig.topper

Subscribers: davide, danielcdh, mgorny, aprantl, eraman, JDevlieghere, llvm-commits

Differential Revision: https://reviews.llvm.org/D54052

llvm-svn: 347596

8 files changed, 290 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/discriminate-mem-ops.ll b/llvm/test/CodeGen/X86/discriminate-mem-ops.ll
new file mode 100644
index 00000000000..b77a91fafd2
--- /dev/null
+++ b/llvm/test/CodeGen/X86/discriminate-mem-ops.ll
@@ -0,0 +1,55 @@
+; RUN: llc < %s | FileCheck %s
+;
+; original source, compiled with -O3 -gmlt -fdebug-info-for-profiling:
+; int sum(int* arr, int pos1, int pos2) {
+;   return arr[pos1] + arr[pos2];
+; }
+;
+; ModuleID = 'test.cc'
+source_filename = "test.cc"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind readonly uwtable
+define i32 @sum(i32* %arr, i32 %pos1, i32 %pos2) !dbg !7 {
+entry:
+  %idxprom = sext i32 %pos1 to i64, !dbg !9
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %idxprom, !dbg !9
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !9, !tbaa !10
+  %idxprom1 = sext i32 %pos2 to i64, !dbg !14
+  %arrayidx2 = getelementptr inbounds i32, i32* %arr, i64 %idxprom1, !dbg !14
+  %1 = load i32, i32* %arrayidx2, align 4, !dbg !14, !tbaa !10
+  %add = add nsw i32 %1, %0, !dbg !15
+  ret i32 %add, !dbg !16
+}
+
+attributes #0 = { "target-cpu"="x86-64" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "test.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 7.0.0 (trunk 322155) (llvm/trunk 322159)"}
+!7 = distinct !DISubprogram(name: "sum", linkageName: "sum", scope: !1, file: !1, line: 1, type: !8, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!8 = !DISubroutineType(types: !2)
+!9 = !DILocation(line: 2, column: 10, scope: !7)
+!10 = !{!11, !11, i64 0}
+!11 = !{!"int", !12, i64 0}
+!12 = !{!"omnipotent char", !13, i64 0}
+!13 = !{!"Simple C++ TBAA"}
+!14 = !DILocation(line: 2, column: 22, scope: !7)
+!15 = !DILocation(line: 2, column: 20, scope: !7)
+!16 = !DILocation(line: 2, column: 3, scope: !7)
+
+;CHECK-LABEL: sum:
+;CHECK:       # %bb.0:
+;CHECK:       movl (%rdi,%rax,4), %eax
+;CHECK-NEXT:  .loc 1 2 20 discriminator 2  # test.cc:2:20
+;CHECK-NEXT:  addl (%rdi,%rcx,4), %eax
+;CHECK-NEXT:  .loc 1 2 3                   # test.cc:2:3
diff --git a/llvm/test/CodeGen/X86/insert-prefetch-inline.afdo b/llvm/test/CodeGen/X86/insert-prefetch-inline.afdo
new file mode 100644
index 00000000000..83b30f6e210
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insert-prefetch-inline.afdo
@@ -0,0 +1,4 @@
+caller:0:0
+ 2:sum:0
+  3: 0 __prefetch_nta_0:23456
+  3.1: 0 __prefetch_nta_0:8764 __prefetch_nta_1:64
\ No newline at end of file
diff --git a/llvm/test/CodeGen/X86/insert-prefetch-inline.ll b/llvm/test/CodeGen/X86/insert-prefetch-inline.ll
new file mode 100644
index 00000000000..5f8373f9480
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insert-prefetch-inline.ll
@@ -0,0 +1,76 @@
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch-inline.afdo | FileCheck %s
+;
+; Verify we can insert prefetch instructions in code belonging to inlined
+; functions.
+;
+; ModuleID = 'test.cc'
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind readonly uwtable
+define dso_local i32 @sum(i32* nocapture readonly %arr, i32 %pos1, i32 %pos2) local_unnamed_addr #0 !dbg !7 {
+entry:
+  %idxprom = sext i32 %pos1 to i64, !dbg !10
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %idxprom, !dbg !10
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !10, !tbaa !11
+  %idxprom1 = sext i32 %pos2 to i64, !dbg !15
+  %arrayidx2 = getelementptr inbounds i32, i32* %arr, i64 %idxprom1, !dbg !15
+  %1 = load i32, i32* %arrayidx2, align 4, !dbg !15, !tbaa !11
+  %add = add nsw i32 %1, %0, !dbg !16
+  ret i32 %add, !dbg !17
+}
+
+; "caller" inlines "sum". The associated .afdo file references instructions
+; in "caller" that came from "sum"'s inlining.
+;
+; Function Attrs: norecurse nounwind readonly uwtable
+define dso_local i32 @caller(i32* nocapture readonly %arr) local_unnamed_addr #0 !dbg !18 {
+entry:
+  %0 = load i32, i32* %arr, align 4, !dbg !19, !tbaa !11
+  %arrayidx2.i = getelementptr inbounds i32, i32* %arr, i64 2, !dbg !21
+  %1 = load i32, i32* %arrayidx2.i, align 4, !dbg !21, !tbaa !11
+  %add.i = add nsw i32 %1, %0, !dbg !22
+  ret i32 %add.i, !dbg !23
+}
+
+attributes #0 = { "target-cpu"="x86-64" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 7.0.0 (trunk 324940) (llvm/trunk 324941)", isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "test.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 7.0.0 (trunk 324940) (llvm/trunk 324941)"}
+!7 = distinct !DISubprogram(name: "sum", linkageName: "sum", scope: !8, file: !8, line: 3, type: !9, isLocal: false, isDefinition: true, scopeLine: 3, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!8 = !DIFile(filename: "./test.h", directory: "/tmp")
+!9 = !DISubroutineType(types: !2)
+!10 = !DILocation(line: 6, column: 10, scope: !7)
+!11 = !{!12, !12, i64 0}
+!12 = !{!"int", !13, i64 0}
+!13 = !{!"omnipotent char", !14, i64 0}
+!14 = !{!"Simple C++ TBAA"}
+!15 = !DILocation(line: 6, column: 22, scope: !7)
+!16 = !DILocation(line: 6, column: 20, scope: !7)
+!17 = !DILocation(line: 6, column: 3, scope: !7)
+!18 = distinct !DISubprogram(name: "caller", linkageName: "caller", scope: !1, file: !1, line: 4, type: !9, isLocal: false, isDefinition: true, scopeLine: 4, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!19 = !DILocation(line: 6, column: 10, scope: !7, inlinedAt: !20)
+!20 = distinct !DILocation(line: 6, column: 10, scope: !18)
+!21 = !DILocation(line: 6, column: 22, scope: !7, inlinedAt: !20)
+!22 = !DILocation(line: 6, column: 20, scope: !7, inlinedAt: !20)
+!23 = !DILocation(line: 6, column: 3, scope: !18)
+
+; CHECK-LABEL: caller:
+; CHECK-LABEL: # %bb.0:
+; CHECK-NEXT: .loc 1 6 22 prologue_end
+; CHECK-NEXT: prefetchnta 23464(%rdi)
+; CHECK-NEXT: movl 8(%rdi), %eax
+; CHECK-NEXT: .loc 1 6 20 is_stmt 0 discriminator 2
+; CHECK-NEXT: prefetchnta 8764(%rdi)
+; CHECK-NEXT: prefetchnta 64(%rdi)
+; CHECK-NEXT: addl (%rdi), %eax
diff --git a/llvm/test/CodeGen/X86/insert-prefetch-no-MachineMemOperand.ll b/llvm/test/CodeGen/X86/insert-prefetch-no-MachineMemOperand.ll
new file mode 100644
index 00000000000..9d7757270d7
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insert-prefetch-no-MachineMemOperand.ll
@@ -0,0 +1,46 @@
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch-nomemop.afdo | FileCheck %s
+; ModuleID = 'prefetch.cc'
+source_filename = "prefetch.cc"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind uwtable
+define dso_local i32 @main() local_unnamed_addr #0 !dbg !7 {
+entry:
+  tail call void @llvm.prefetch(i8* inttoptr (i64 291 to i8*), i32 0, i32 0, i32 1), !dbg !9
+  tail call void @llvm.x86.avx512.gatherpf.dpd.512(i8 97, <8 x i32> undef, i8* null, i32 1, i32 2), !dbg !10
+  ret i32 291, !dbg !11
+}
+
+; Function Attrs: inaccessiblemem_or_argmemonly nounwind
+declare void @llvm.prefetch(i8* nocapture readonly, i32, i32, i32) #1
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.x86.avx512.gatherpf.dpd.512(i8, <8 x i32>, i8*, i32, i32) #2
+
+attributes #0 = {"target-cpu"="x86-64" "target-features"="+avx512pf,+sse4.2,+ssse3"}
+attributes #1 = { inaccessiblemem_or_argmemonly nounwind }
+attributes #2 = { argmemonly nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "prefetch.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 7.0.0 (trunk 327078) (llvm/trunk 327086)"}
+!7 = distinct !DISubprogram(name: "main", scope: !1, file: !1, line: 8, type: !8, isLocal: false, isDefinition: true, scopeLine: 8, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!8 = !DISubroutineType(types: !2)
+!9 = !DILocation(line: 12, column: 3, scope: !7)
+!10 = !DILocation(line: 14, column: 3, scope: !7)
+!11 = !DILocation(line: 15, column: 3, scope: !7)
+
+;CHECK-LABEL: main:
+;CHECK:       # %bb.0:
+;CHECK:       prefetchnta 291
+;CHECK:       prefetchnta 42(%rax,%ymm0)
+;CHECK-NEXT:  vgatherpf1dpd (%rax,%ymm0) {%k1}
diff --git a/llvm/test/CodeGen/X86/insert-prefetch-nomemop.afdo b/llvm/test/CodeGen/X86/insert-prefetch-nomemop.afdo
new file mode 100644
index 00000000000..6385a498b8f
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insert-prefetch-nomemop.afdo
@@ -0,0 +1,2 @@
+main:0:0
+ 6: 0 __prefetch_nta_0:42
\ No newline at end of file
diff --git a/llvm/test/CodeGen/X86/insert-prefetch-other.afdo b/llvm/test/CodeGen/X86/insert-prefetch-other.afdo
new file mode 100644
index 00000000000..783da34f7f8
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insert-prefetch-other.afdo
@@ -0,0 +1,3 @@
+sum:0:0
+ 1: 0 __prefetch_t0_1:0 __prefetch_t2_0:42
+ 1.1: 0 __prefetch_t1_0:18446744073709551615
diff --git a/llvm/test/CodeGen/X86/insert-prefetch.afdo b/llvm/test/CodeGen/X86/insert-prefetch.afdo
new file mode 100644
index 00000000000..96487e85eaa
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insert-prefetch.afdo
@@ -0,0 +1,3 @@
+sum:0:0
+ 1: 0 __prefetch_nta_1:0 __prefetch_nta_0:42
+ 1.1: 0 __prefetch_nta_0:18446744073709551615
diff --git a/llvm/test/CodeGen/X86/insert-prefetch.ll b/llvm/test/CodeGen/X86/insert-prefetch.ll
new file mode 100644
index 00000000000..9e77772df77
--- /dev/null
+++ b/llvm/test/CodeGen/X86/insert-prefetch.ll
@@ -0,0 +1,101 @@
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch.afdo | FileCheck %s
+; RUN: llc < %s -prefetch-hints-file=%S/insert-prefetch-other.afdo | FileCheck %s -check-prefix=OTHERS
+;
+; original source, compiled with -O3 -gmlt -fdebug-info-for-profiling:
+; int sum(int* arr, int pos1, int pos2) {
+;   return arr[pos1] + arr[pos2];
+; }
+;
+; NOTE: debug line numbers were adjusted such that the function would start
+; at line 15 (an arbitrary number). The sample profile file format uses
+; offsets from the start of the symbol instead of file-relative line numbers.
+; The .afdo file reflects that - the instructions are offset '1'.
+;
+; ModuleID = 'test.cc'
+source_filename = "test.cc"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @sum(i32* %arr, i32 %pos1, i32 %pos2) !dbg !35 !prof !37 {
+entry:
+  %idxprom = sext i32 %pos1 to i64, !dbg !38
+  %arrayidx = getelementptr inbounds i32, i32* %arr, i64 %idxprom, !dbg !38
+  %0 = load i32, i32* %arrayidx, align 4, !dbg !38, !tbaa !39
+  %idxprom1 = sext i32 %pos2 to i64, !dbg !43
+  %arrayidx2 = getelementptr inbounds i32, i32* %arr, i64 %idxprom1, !dbg !43
+  %1 = load i32, i32* %arrayidx2, align 4, !dbg !43, !tbaa !39
+  %add = add nsw i32 %1, %0, !dbg !44
+  ret i32 %add, !dbg !45
+}
+
+attributes #0 = { "target-cpu"="x86-64" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5, !6}
+!llvm.ident = !{!33}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, debugInfoForProfiling: true)
+!1 = !DIFile(filename: "test.cc", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{i32 1, !"ProfileSummary", !7}
+!7 = !{!8, !9, !10, !11, !12, !13, !14, !15}
+!8 = !{!"ProfileFormat", !"SampleProfile"}
+!9 = !{!"TotalCount", i64 0}
+!10 = !{!"MaxCount", i64 0}
+!11 = !{!"MaxInternalCount", i64 0}
+!12 = !{!"MaxFunctionCount", i64 0}
+!13 = !{!"NumCounts", i64 2}
+!14 = !{!"NumFunctions", i64 1}
+!15 = !{!"DetailedSummary", !16}
+!16 = !{!17, !18, !19, !20, !21, !22, !22, !23, !23, !24, !25, !26, !27, !28, !29, !30, !31, !32}
+!17 = !{i32 10000, i64 0, i32 0}
+!18 = !{i32 100000, i64 0, i32 0}
+!19 = !{i32 200000, i64 0, i32 0}
+!20 = !{i32 300000, i64 0, i32 0}
+!21 = !{i32 400000, i64 0, i32 0}
+!22 = !{i32 500000, i64 0, i32 0}
+!23 = !{i32 600000, i64 0, i32 0}
+!24 = !{i32 700000, i64 0, i32 0}
+!25 = !{i32 800000, i64 0, i32 0}
+!26 = !{i32 900000, i64 0, i32 0}
+!27 = !{i32 950000, i64 0, i32 0}
+!28 = !{i32 990000, i64 0, i32 0}
+!29 = !{i32 999000, i64 0, i32 0}
+!30 = !{i32 999900, i64 0, i32 0}
+!31 = !{i32 999990, i64 0, i32 0}
+!32 = !{i32 999999, i64 0, i32 0}
+!33 = !{!"clang version 7.0.0 (trunk 322593) (llvm/trunk 322526)"}
+!35 = distinct !DISubprogram(name: "sum", linkageName: "sum", scope: !1, file: !1, line: 15, type: !36, isLocal: false, isDefinition: true, scopeLine: 15, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!36 = !DISubroutineType(types: !2)
+!37 = !{!"function_entry_count", i64 -1}
+!38 = !DILocation(line: 16, column: 10, scope: !35)
+!39 = !{!40, !40, i64 0}
+!40 = !{!"int", !41, i64 0}
+!41 = !{!"omnipotent char", !42, i64 0}
+!42 = !{!"Simple C++ TBAA"}
+!43 = !DILocation(line: 16, column: 22, scope: !35)
+!44 = !DILocation(line: 16, column: 20, scope: !35)
+!45 = !DILocation(line: 16, column: 3, scope: !35)
+
+;CHECK-LABEL: sum:
+;CHECK:       # %bb.0:
+;CHECK:       prefetchnta 42(%rdi,%rax,4)
+;CHECK-NEXT:  prefetchnta (%rdi,%rax,4)
+;CHECK-NEXT:  movl (%rdi,%rax,4), %eax
+;CHECK-NEXT:  .loc 1 16 20 discriminator 2  # test.cc:16:20
+;CHECK-NEXT:  prefetchnta -1(%rdi,%rcx,4)
+;CHECK-NEXT:  addl (%rdi,%rcx,4), %eax
+;CHECK-NEXT:  .loc 1 16 3                   # test.cc:16:3
+
+;OTHERS-LABEL: sum:
+;OTHERS:       # %bb.0:
+;OTHERS:       prefetcht2 42(%rdi,%rax,4)
+;OTHERS-NEXT:  prefetcht0 (%rdi,%rax,4)
+;OTHERS-NEXT:  movl (%rdi,%rax,4), %eax
+;OTHERS-NEXT:  .loc 1 16 20 discriminator 2  # test.cc:16:20
+;OTHERS-NEXT:  prefetcht1 -1(%rdi,%rcx,4)
+;OTHERS-NEXT:  addl (%rdi,%rcx,4), %eax
+;OTHERS-NEXT:  .loc 1 16 3                   # test.cc:16:3