This is an archive of the discontinued LLVM Phabricator instance.

Differential D93792

[X86] Refactor AMX test case, remove unnecessary code.
ClosedPublic

Authored by LuoYuanke on Dec 23 2020, 7:37 PM.

Details

Reviewers
craig.topper
pengfei
xiangzhangllvm
LiuChen3
Commits
rG6e9755bb80c8: [X86] Refactor AMX test case, remove unnecessary code.
Summary

Refactor AMX test case, remove unnecessary code.

Diff Detail

Event Timeline

LuoYuanke created this revision.Dec 23 2020, 7:37 PM
Herald added subscribers: pengfei, qcolombet. · View Herald TranscriptDec 23 2020, 7:37 PM
LuoYuanke requested review of this revision.Dec 23 2020, 7:37 PM
Herald added a project: Restricted Project. · View Herald TranscriptDec 23 2020, 7:37 PM
Herald added a subscriber: llvm-commits. · View Herald Transcript
Harbormaster completed remote builds in B83450: Diff 313644.Dec 23 2020, 7:38 PM
LuoYuanke edited the summary of this revision. (Show Details)Dec 23 2020, 7:39 PM
LuoYuanke added reviewers: craig.topper, pengfei, xiangzhangllvm, LiuChen3.
LuoYuanke added a parent revision: D91927: [X86] Add x86_amx type for intel AMX..
LuoYuanke added a subscriber: annita.zhang.
pengfei accepted this revision.Dec 23 2020, 10:16 PM

LGTM.

llvm/test/CodeGen/X86/AMX/amx-across-func.ll
2–3

Nit: these lines also can be removed. The same below.

This revision is now accepted and ready to land.Dec 23 2020, 10:16 PM
LuoYuanke updated this revision to Diff 313658.Dec 23 2020, 10:50 PM

Address Pengfei's comments.

Harbormaster completed remote builds in B83462: Diff 313658.Dec 23 2020, 11:47 PM
LuoYuanke updated this revision to Diff 314079.Dec 29 2020, 11:23 PM

Rebase

LuoYuanke updated this revision to Diff 314081.Dec 29 2020, 11:39 PM

Remove datalayout from test case.

This revision was landed with ongoing or failed builds.Dec 29 2020, 11:44 PM
Closed by commit rG6e9755bb80c8: [X86] Refactor AMX test case, remove unnecessary code. (authored by LuoYuanke). · Explain Why
This revision was automatically updated to reflect the committed changes.
LuoYuanke added a commit: rG6e9755bb80c8: [X86] Refactor AMX test case, remove unnecessary code..
Harbormaster completed remote builds in B83731: Diff 314081.Dec 30 2020, 12:10 AM
Harbormaster completed remote builds in B83730: Diff 314079.Dec 30 2020, 12:17 AM
LuoYuanke added a child revision: D92837: [X86] Support tilezero intrinsic and c interface for AMX..Dec 30 2020, 5:32 PM

Revision Contents

PathSize
llvm/
test/
CodeGen/
X86/
AMX/
28 lines
34 lines
1 line
50 lines
136 lines

Diff 314083

llvm/test/CodeGen/X86/AMX/amx-across-func.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
pengfeiUnsubmitted
Not Done
ReplyInline Actions

Nit: these lines also can be removed. The same below.

pengfei: Nit: these lines also can be removed. The same below.
%struct.__tile_str = type <{ i16, i16, [60 x i8], <256 x i32> }> %struct.__tile_str = type <{ i16, i16, [60 x i8], <256 x i32> }>
@buf = dso_local global [3072 x i8] zeroinitializer, align 16 @buf = dso_local global [3072 x i8] zeroinitializer, align 16
define dso_local void @test_api(i16 signext %0, i16 signext %1) local_unnamed_addr #2 { define dso_local void @test_api(i16 signext %0, i16 signext %1) local_unnamed_addr {
; CHECK-LABEL: test_api: ; CHECK-LABEL: test_api:
; CHECK: # %bb.0: ; CHECK: # %bb.0:
; CHECK-NEXT: pushq %rbp ; CHECK-NEXT: pushq %rbp
; CHECK-NEXT: .cfi_def_cfa_offset 16 ; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: pushq %r15 ; CHECK-NEXT: pushq %r15
; CHECK-NEXT: .cfi_def_cfa_offset 24 ; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: pushq %r14 ; CHECK-NEXT: pushq %r14
; CHECK-NEXT: .cfi_def_cfa_offset 32 ; CHECK-NEXT: .cfi_def_cfa_offset 32
▲ Show 20 Lines • Show All 47 Lines • ▼ Show 20 Lines
; CHECK-NEXT: popq %r14 ; CHECK-NEXT: popq %r14
; CHECK-NEXT: .cfi_def_cfa_offset 24 ; CHECK-NEXT: .cfi_def_cfa_offset 24
; CHECK-NEXT: popq %r15 ; CHECK-NEXT: popq %r15
; CHECK-NEXT: .cfi_def_cfa_offset 16 ; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: popq %rbp ; CHECK-NEXT: popq %rbp
; CHECK-NEXT: .cfi_def_cfa_offset 8 ; CHECK-NEXT: .cfi_def_cfa_offset 8
; CHECK-NEXT: tilerelease ; CHECK-NEXT: tilerelease
; CHECK-NEXT: retq ; CHECK-NEXT: retq
%3 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 8, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32) #4 %3 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 8, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32)
%4 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 1024), i64 32) #4 %4 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 1024), i64 32)
tail call void (...) @foo() #4 tail call void (...) @foo()
%5 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32) #4 %5 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32)
%6 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %0, i16 %1, i16 8, x86_amx %5, x86_amx %3, x86_amx %4) #4 %6 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %0, i16 %1, i16 8, x86_amx %5, x86_amx %3, x86_amx %4)
tail call void @llvm.x86.tilestored64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32, x86_amx %6) #4 tail call void @llvm.x86.tilestored64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32, x86_amx %6)
ret void ret void
} }
declare dso_local void @foo(...) local_unnamed_addr #3 declare dso_local void @foo(...) local_unnamed_addr
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64) #4 declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx) #4 declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx) #4 declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
attributes #2 = { nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="8192" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile,+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #3 = { "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile,+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #4 = { nounwind }

llvm/test/CodeGen/X86/AMX/amx-config.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -verify-machineinstrs | FileCheck %s ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@buf = dso_local global [1024 x i8] zeroinitializer, align 16 @buf = dso_local global [1024 x i8] zeroinitializer, align 16
@buf2 = dso_local global [1024 x i8] zeroinitializer, align 16 @buf2 = dso_local global [1024 x i8] zeroinitializer, align 16
; Function Attrs: nounwind uwtable ; Function Attrs: nounwind uwtable
define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) local_unnamed_addr #2 { define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) local_unnamed_addr {
; CHECK-LABEL: test_api: ; CHECK-LABEL: test_api:
; CHECK: # %bb.0: ; CHECK: # %bb.0:
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: movsbl %sil, %eax ; CHECK-NEXT: movsbl %sil, %eax
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0 ; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %al, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movb %al, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %si, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movw %si, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %al, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movb %al, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %dx, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movw %dx, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %al, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movb %al, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %dx, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movw %dx, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp) ; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: je .LBB0_2 ; CHECK-NEXT: je .LBB0_2
; CHECK-NEXT: # %bb.1: ; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: movl $buf, %ecx ; CHECK-NEXT: movl $buf, %ecx
; CHECK-NEXT: jmp .LBB0_3 ; CHECK-NEXT: jmp .LBB0_3
; CHECK-NEXT: .LBB0_2: ; CHECK-NEXT: .LBB0_2:
; CHECK-NEXT: movl $buf2, %ecx ; CHECK-NEXT: movl $buf2, %ecx
; CHECK-NEXT: .LBB0_3: ; CHECK-NEXT: .LBB0_3:
; CHECK-NEXT: movl $32, %edi ; CHECK-NEXT: movl $32, %edi
; CHECK-NEXT: tileloadd (%rcx,%rdi), %tmm0 ; CHECK-NEXT: tileloadd (%rcx,%rdi), %tmm0
; CHECK-NEXT: tileloadd (%rcx,%rdi), %tmm2 ; CHECK-NEXT: tileloadd (%rcx,%rdi), %tmm2
; CHECK-NEXT: tileloadd (%rcx,%rdi), %tmm1 ; CHECK-NEXT: tileloadd (%rcx,%rdi), %tmm1
; CHECK-NEXT: tdpbssd %tmm2, %tmm0, %tmm1 ; CHECK-NEXT: tdpbssd %tmm2, %tmm0, %tmm1
; CHECK-NEXT: movl $buf, %ecx ; CHECK-NEXT: movl $buf, %ecx
; CHECK-NEXT: movl $32, %esi ; CHECK-NEXT: movl $32, %esi
; CHECK-NEXT: tilestored %tmm1, (%rcx,%rsi) ; CHECK-NEXT: tilestored %tmm1, (%rcx,%rsi)
; CHECK-NEXT: tilerelease ; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper ; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq ; CHECK-NEXT: retq
%4 = icmp eq i32 %0, 0 %4 = icmp eq i32 %0, 0
%5 = shl i16 %1, 8 %5 = shl i16 %1, 8
%6 = ashr exact i16 %5, 8 %6 = ashr exact i16 %5, 8
br i1 %4, label %11, label %7 br i1 %4, label %11, label %7
7: ; preds = %3 7: ; preds = %3
%8 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %8 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%9 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %9 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%10 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %10 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
br label %15 br label %15
11: ; preds = %3 11: ; preds = %3
%12 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32) #3 %12 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32)
%13 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32) #3 %13 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32)
%14 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32) #3 %14 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32)
br label %15 br label %15
15: ; preds = %11, %7 15: ; preds = %11, %7
%16 = phi x86_amx [ %12, %11 ], [ %8, %7 ] %16 = phi x86_amx [ %12, %11 ], [ %8, %7 ]
%17 = phi x86_amx [ %13, %11 ], [ %9, %7 ] %17 = phi x86_amx [ %13, %11 ], [ %9, %7 ]
%18 = phi x86_amx [ %14, %11 ], [ %10, %7 ] %18 = phi x86_amx [ %14, %11 ], [ %10, %7 ]
%19 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %6, i16 %2, i16 %1, x86_amx %18, x86_amx %16, x86_amx %17) #3 %19 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %6, i16 %2, i16 %1, x86_amx %18, x86_amx %16, x86_amx %17)
tail call void @llvm.x86.tilestored64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %19) #3 tail call void @llvm.x86.tilestored64.internal(i16 %6, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %19)
ret void ret void
} }
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64) #3 declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx) #3
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx) #3 declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
attributes #2 = { nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="8192" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile,+avx,+avx2,+avx512f,+cx8,+f16c,+fma,+fxsr,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" } declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
attributes #3 = { nounwind }

llvm/test/CodeGen/X86/AMX/amx-intrinsic-chain.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
define dso_local void @test_chain(i8* %A_mem, i8* %B_mem, i8* %C_mem) local_unnamed_addr { define dso_local void @test_chain(i8* %A_mem, i8* %B_mem, i8* %C_mem) local_unnamed_addr {
; CHECK-LABEL: test_chain: ; CHECK-LABEL: test_chain:
; CHECK: # %bb.0: # %entry ; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0 ; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $16, -{{[0-9]+}}(%rsp) ; CHECK-NEXT: movb $16, -{{[0-9]+}}(%rsp)
▲ Show 20 Lines • Show All 48 Lines • Show Last 20 Lines

llvm/test/CodeGen/X86/AMX/amx-spill.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@buf = dso_local global [1024 x i8] zeroinitializer, align 16 @buf = dso_local global [1024 x i8] zeroinitializer, align 16
@buf2 = dso_local global [1024 x i8] zeroinitializer, align 16 @buf2 = dso_local global [1024 x i8] zeroinitializer, align 16
define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) local_unnamed_addr #2 { define dso_local void @test_api(i32 %0, i16 signext %1, i16 signext %2) local_unnamed_addr {
; CHECK-LABEL: test_api: ; CHECK-LABEL: test_api:
; CHECK: # %bb.0: ; CHECK: # %bb.0:
; CHECK-NEXT: subq $2936, %rsp # imm = 0xB78 ; CHECK-NEXT: subq $2936, %rsp # imm = 0xB78
; CHECK-NEXT: .cfi_def_cfa_offset 2944 ; CHECK-NEXT: .cfi_def_cfa_offset 2944
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0 ; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, {{[0-9]+}}(%rsp) ; CHECK-NEXT: vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, {{[0-9]+}}(%rsp) ; CHECK-NEXT: movb $1, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %dl, {{[0-9]+}}(%rsp) ; CHECK-NEXT: movb %dl, {{[0-9]+}}(%rsp)
▲ Show 20 Lines • Show All 46 Lines • ▼ Show 20 Lines
; CHECK-NEXT: movl $buf, %eax ; CHECK-NEXT: movl $buf, %eax
; CHECK-NEXT: movl $32, %ecx ; CHECK-NEXT: movl $32, %ecx
; CHECK-NEXT: tilestored %tmm0, (%rax,%rcx) ; CHECK-NEXT: tilestored %tmm0, (%rax,%rcx)
; CHECK-NEXT: addq $2936, %rsp # imm = 0xB78 ; CHECK-NEXT: addq $2936, %rsp # imm = 0xB78
; CHECK-NEXT: .cfi_def_cfa_offset 8 ; CHECK-NEXT: .cfi_def_cfa_offset 8
; CHECK-NEXT: tilerelease ; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper ; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq ; CHECK-NEXT: retq
%4 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %4 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%5 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %5 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%6 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %6 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%7 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %7 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%8 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %8 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%9 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %9 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%10 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %10 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%11 = icmp eq i32 %0, 0 %11 = icmp eq i32 %0, 0
br i1 %11, label %16, label %12 br i1 %11, label %16, label %12
12: ; preds = %3 12: ; preds = %3
%13 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %13 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%14 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %14 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
%15 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32) #3 %15 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32)
br label %20 br label %20
16: ; preds = %3 16: ; preds = %3
%17 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32) #3 %17 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %1, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32)
%18 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32) #3 %18 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32)
%19 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32) #3 %19 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %1, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf2, i64 0, i64 0), i64 32)
br label %20 br label %20
20: ; preds = %16, %12 20: ; preds = %16, %12
%21 = phi x86_amx [ %17, %16 ], [ %13, %12 ] %21 = phi x86_amx [ %17, %16 ], [ %13, %12 ]
%22 = phi x86_amx [ %18, %16 ], [ %14, %12 ] %22 = phi x86_amx [ %18, %16 ], [ %14, %12 ]
%23 = phi x86_amx [ %19, %16 ], [ %15, %12 ] %23 = phi x86_amx [ %19, %16 ], [ %15, %12 ]
%24 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %1, i16 %2, i16 %1, x86_amx %23, x86_amx %21, x86_amx %22) #3 %24 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %1, i16 %2, i16 %1, x86_amx %23, x86_amx %21, x86_amx %22)
%25 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %1, i16 %2, i16 %2, x86_amx %6, x86_amx %24, x86_amx %5) #3 %25 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %1, i16 %2, i16 %2, x86_amx %6, x86_amx %24, x86_amx %5)
%26 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %1, i16 %2, i16 %2, x86_amx %8, x86_amx %25, x86_amx %7) #3 %26 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %1, i16 %2, i16 %2, x86_amx %8, x86_amx %25, x86_amx %7)
%27 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %2, i16 %2, i16 %2, x86_amx %10, x86_amx %26, x86_amx %9) #3 %27 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %2, i16 %2, i16 %2, x86_amx %10, x86_amx %26, x86_amx %9)
tail call void @llvm.x86.tilestored64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %27) #3 tail call void @llvm.x86.tilestored64.internal(i16 %2, i16 %2, i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %27)
ret void ret void
} }
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64) #3 declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx) #3 declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx) #3 declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
attributes #2 = { nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="8192" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile,+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #3 = { nounwind }

llvm/test/CodeGen/X86/AMX/amx-type.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -lower-amx-type %s -S | FileCheck %s ; RUN: opt -lower-amx-type %s -S | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
%struct.__tile_str = type { i16, i16, <256 x i32> } %struct.__tile_str = type { i16, i16, <256 x i32> }
@buf = dso_local global [1024 x i8] zeroinitializer, align 16 @buf = dso_local global [1024 x i8] zeroinitializer, align 16
@buf2 = dso_local global [1024 x i8] zeroinitializer, align 16 @buf2 = dso_local global [1024 x i8] zeroinitializer, align 16
; test bitcast x86_amx to <256 x i32> ; test bitcast x86_amx to <256 x i32>
define dso_local void @test_user_empty(i16 %m, i16 %n, i8 *%buf, i64 %s) #2 { define dso_local void @test_user_empty(i16 %m, i16 %n, i8 *%buf, i64 %s) {
; CHECK-LABEL: @test_user_empty( ; CHECK-LABEL: @test_user_empty(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[M:%.*]], i16 [[N:%.*]], i8* [[BUF:%.*]], i64 [[S:%.*]]) [[ATTR3:#.*]] ; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[M:%.*]], i16 [[N:%.*]], i8* [[BUF:%.*]], i64 [[S:%.*]])
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%t1 = call x86_amx @llvm.x86.tileloadd64.internal(i16 %m, i16 %n, i8* %buf, i64 %s) #3 %t1 = call x86_amx @llvm.x86.tileloadd64.internal(i16 %m, i16 %n, i8* %buf, i64 %s)
%t2 = bitcast x86_amx %t1 to <256 x i32> %t2 = bitcast x86_amx %t1 to <256 x i32>
ret void ret void
} }
; test bitcast <256 x i32> to x86_amx ; test bitcast <256 x i32> to x86_amx
define dso_local void @test_user_empty2(<256 x i32> %in) #2 { define dso_local void @test_user_empty2(<256 x i32> %in) {
; CHECK-LABEL: @test_user_empty2( ; CHECK-LABEL: @test_user_empty2(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%t = bitcast <256 x i32> %in to x86_amx %t = bitcast <256 x i32> %in to x86_amx
ret void ret void
} }
define dso_local <256 x i32> @test_amx_load_bitcast(<256 x i32>* %in, i16 %m, i16 %n, i8 *%buf, i64 %s) #2 { define dso_local <256 x i32> @test_amx_load_bitcast(<256 x i32>* %in, i16 %m, i16 %n, i8 *%buf, i64 %s) {
; CHECK-LABEL: @test_amx_load_bitcast( ; CHECK-LABEL: @test_amx_load_bitcast(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[T1:%.*]] = load <256 x i32>, <256 x i32>* [[IN:%.*]], align 64 ; CHECK-NEXT: [[T1:%.*]] = load <256 x i32>, <256 x i32>* [[IN:%.*]], align 64
; CHECK-NEXT: [[TMP0:%.*]] = bitcast <256 x i32>* [[IN]] to i8* ; CHECK-NEXT: [[TMP0:%.*]] = bitcast <256 x i32>* [[IN]] to i8*
; CHECK-NEXT: [[TMP1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[M:%.*]], i16 [[N:%.*]], i8* [[TMP0]], i64 64) ; CHECK-NEXT: [[TMP1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[M:%.*]], i16 [[N:%.*]], i8* [[TMP0]], i64 64)
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[M]], i16 [[N]], i8* [[BUF:%.*]], i64 [[S:%.*]], x86_amx [[TMP1]]) [[ATTR3]] ; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[M]], i16 [[N]], i8* [[BUF:%.*]], i64 [[S:%.*]], x86_amx [[TMP1]])
; CHECK-NEXT: ret <256 x i32> [[T1]] ; CHECK-NEXT: ret <256 x i32> [[T1]]
; ;
entry: entry:
%t1 = load <256 x i32>, <256 x i32>* %in, align 64 %t1 = load <256 x i32>, <256 x i32>* %in, align 64
%t2 = bitcast <256 x i32> %t1 to x86_amx %t2 = bitcast <256 x i32> %t1 to x86_amx
call void @llvm.x86.tilestored64.internal(i16 %m, i16 %n, i8* %buf, i64 %s, x86_amx %t2) #3 call void @llvm.x86.tilestored64.internal(i16 %m, i16 %n, i8* %buf, i64 %s, x86_amx %t2)
ret <256 x i32> %t1 ret <256 x i32> %t1
} }
define dso_local <256 x i32> @test_amx_bitcast_store(<256 x i32>* %out, i16 %m, i16 %n, i8 *%buf, i64 %s) #2 { define dso_local <256 x i32> @test_amx_bitcast_store(<256 x i32>* %out, i16 %m, i16 %n, i8 *%buf, i64 %s) {
; CHECK-LABEL: @test_amx_bitcast_store( ; CHECK-LABEL: @test_amx_bitcast_store(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[M:%.*]], i16 [[M]], i8* [[BUF:%.*]], i64 [[S:%.*]]) [[ATTR3]] ; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[M:%.*]], i16 [[M]], i8* [[BUF:%.*]], i64 [[S:%.*]])
; CHECK-NEXT: [[TMP0:%.*]] = bitcast <256 x i32>* [[OUT:%.*]] to i8* ; CHECK-NEXT: [[TMP0:%.*]] = bitcast <256 x i32>* [[OUT:%.*]] to i8*
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[M]], i16 [[M]], i8* [[TMP0]], i64 64, x86_amx [[T1]]) ; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[M]], i16 [[M]], i8* [[TMP0]], i64 64, x86_amx [[T1]])
; CHECK-NEXT: [[TMP1:%.*]] = load <256 x i32>, <256 x i32>* [[OUT]], align 1024 ; CHECK-NEXT: [[TMP1:%.*]] = load <256 x i32>, <256 x i32>* [[OUT]], align 1024
; CHECK-NEXT: ret <256 x i32> [[TMP1]] ; CHECK-NEXT: ret <256 x i32> [[TMP1]]
; ;
entry: entry:
%t1 = call x86_amx @llvm.x86.tileloadd64.internal(i16 %m, i16 %m, i8* %buf, i64 %s) #3 %t1 = call x86_amx @llvm.x86.tileloadd64.internal(i16 %m, i16 %m, i8* %buf, i64 %s)
%t2 = bitcast x86_amx %t1 to <256 x i32> %t2 = bitcast x86_amx %t1 to <256 x i32>
store <256 x i32> %t2, <256 x i32>* %out store <256 x i32> %t2, <256 x i32>* %out
ret <256 x i32> %t2 ret <256 x i32> %t2
} }
define dso_local void @test_src_add(<256 x i32> %x, <256 x i32> %y, i16 %r, i16 %c, i8* %buf, i64 %s) #2 { define dso_local void @test_src_add(<256 x i32> %x, <256 x i32> %y, i16 %r, i16 %c, i8* %buf, i64 %s) {
; CHECK-LABEL: @test_src_add( ; CHECK-LABEL: @test_src_add(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64 ; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: [[ADD:%.*]] = add <256 x i32> [[Y:%.*]], [[X:%.*]] ; CHECK-NEXT: [[ADD:%.*]] = add <256 x i32> [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = bitcast <256 x i32>* [[TMP0]] to i8* ; CHECK-NEXT: [[TMP1:%.*]] = bitcast <256 x i32>* [[TMP0]] to i8*
; CHECK-NEXT: store <256 x i32> [[ADD]], <256 x i32>* [[TMP0]], align 1024 ; CHECK-NEXT: store <256 x i32> [[ADD]], <256 x i32>* [[TMP0]], align 1024
; CHECK-NEXT: [[TMP2:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[R:%.*]], i16 [[C:%.*]], i8* [[TMP1]], i64 64) ; CHECK-NEXT: [[TMP2:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[R:%.*]], i16 [[C:%.*]], i8* [[TMP1]], i64 64)
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[R]], i16 [[C]], i8* [[BUF:%.*]], i64 [[S:%.*]], x86_amx [[TMP2]]) [[ATTR3]] ; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[R]], i16 [[C]], i8* [[BUF:%.*]], i64 [[S:%.*]], x86_amx [[TMP2]])
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%add = add <256 x i32> %y, %x %add = add <256 x i32> %y, %x
%t = bitcast <256 x i32> %add to x86_amx %t = bitcast <256 x i32> %add to x86_amx
call void @llvm.x86.tilestored64.internal(i16 %r, i16 %c, i8* %buf, i64 %s, x86_amx %t) #3 call void @llvm.x86.tilestored64.internal(i16 %r, i16 %c, i8* %buf, i64 %s, x86_amx %t)
ret void ret void
} }
define dso_local void @test_src_add2(<256 x i32> %x, i16 %r, i16 %c, i8* %buf, i64 %s) #2 { define dso_local void @test_src_add2(<256 x i32> %x, i16 %r, i16 %c, i8* %buf, i64 %s) {
; CHECK-LABEL: @test_src_add2( ; CHECK-LABEL: @test_src_add2(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64 ; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[R:%.*]], i16 [[C:%.*]], i8* [[BUF:%.*]], i64 [[S:%.*]]) [[ATTR3]] ; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[R:%.*]], i16 [[C:%.*]], i8* [[BUF:%.*]], i64 [[S:%.*]])
; CHECK-NEXT: [[TMP1:%.*]] = bitcast <256 x i32>* [[TMP0]] to i8* ; CHECK-NEXT: [[TMP1:%.*]] = bitcast <256 x i32>* [[TMP0]] to i8*
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[R]], i16 [[C]], i8* [[TMP1]], i64 64, x86_amx [[T1]]) ; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[R]], i16 [[C]], i8* [[TMP1]], i64 64, x86_amx [[T1]])
; CHECK-NEXT: [[TMP2:%.*]] = load <256 x i32>, <256 x i32>* [[TMP0]], align 1024 ; CHECK-NEXT: [[TMP2:%.*]] = load <256 x i32>, <256 x i32>* [[TMP0]], align 1024
; CHECK-NEXT: [[ADD:%.*]] = add <256 x i32> [[TMP2]], [[X:%.*]] ; CHECK-NEXT: [[ADD:%.*]] = add <256 x i32> [[TMP2]], [[X:%.*]]
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%t1 = call x86_amx @llvm.x86.tileloadd64.internal(i16 %r, i16 %c, i8* %buf, i64 %s) #3 %t1 = call x86_amx @llvm.x86.tileloadd64.internal(i16 %r, i16 %c, i8* %buf, i64 %s)
%t2 = bitcast x86_amx %t1 to <256 x i32> %t2 = bitcast x86_amx %t1 to <256 x i32>
%add = add <256 x i32> %t2, %x %add = add <256 x i32> %t2, %x
ret void ret void
} }
define dso_local void @test_load(i8* %in, i8* %out) local_unnamed_addr #2 { define dso_local void @test_load(i8* %in, i8* %out) local_unnamed_addr {
; CHECK-LABEL: @test_load( ; CHECK-LABEL: @test_load(
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[IN:%.*]] to <256 x i32>* ; CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[IN:%.*]] to <256 x i32>*
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[OUT:%.*]] to <256 x i32>* ; CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[OUT:%.*]] to <256 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <256 x i32>, <256 x i32>* [[TMP1]], align 64, [[TBAA2:!tbaa !.*]] ; CHECK-NEXT: [[TMP3:%.*]] = load <256 x i32>, <256 x i32>* [[TMP1]], align 64
; CHECK-NEXT: store <256 x i32> [[TMP3]], <256 x i32>* [[TMP2]], align 64, [[TBAA2]] ; CHECK-NEXT: store <256 x i32> [[TMP3]], <256 x i32>* [[TMP2]], align 64
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
%1 = bitcast i8* %in to <256 x i32>* %1 = bitcast i8* %in to <256 x i32>*
%2 = bitcast i8* %out to <256 x i32>* %2 = bitcast i8* %out to <256 x i32>*
%3 = load <256 x i32>, <256 x i32>* %1, align 64, !tbaa !8 %3 = load <256 x i32>, <256 x i32>* %1, align 64
store <256 x i32> %3, <256 x i32>* %2, align 64, !tbaa !8 store <256 x i32> %3, <256 x i32>* %2, align 64
ret void ret void
} }
define dso_local <256 x i32> @foo(<256 x i32>* nocapture readonly byval(<256 x i32>) align 1024 %0, <256 x i32>* nocapture readonly byval(<256 x i32>) align 1024 %1) local_unnamed_addr #0 { define dso_local <256 x i32> @foo(<256 x i32>* nocapture readonly byval(<256 x i32>) align 1024 %0, <256 x i32>* nocapture readonly byval(<256 x i32>) align 1024 %1) local_unnamed_addr {
; CHECK-LABEL: @foo( ; CHECK-LABEL: @foo(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[X:%.*]] = load <256 x i32>, <256 x i32>* [[TMP0:%.*]], align 1024, [[TBAA5:!tbaa !.*]] ; CHECK-NEXT: [[X:%.*]] = load <256 x i32>, <256 x i32>* [[TMP0:%.*]], align 1024
; CHECK-NEXT: [[Y:%.*]] = load <256 x i32>, <256 x i32>* [[TMP1:%.*]], align 1024, [[TBAA5]] ; CHECK-NEXT: [[Y:%.*]] = load <256 x i32>, <256 x i32>* [[TMP1:%.*]], align 1024
; CHECK-NEXT: [[ADD:%.*]] = add <256 x i32> [[Y]], [[X]] ; CHECK-NEXT: [[ADD:%.*]] = add <256 x i32> [[Y]], [[X]]
; CHECK-NEXT: ret <256 x i32> [[ADD]] ; CHECK-NEXT: ret <256 x i32> [[ADD]]
; ;
entry: entry:
%x = load <256 x i32>, <256 x i32>* %0, align 1024, !tbaa !2 %x = load <256 x i32>, <256 x i32>* %0, align 1024
%y = load <256 x i32>, <256 x i32>* %1, align 1024, !tbaa !2 %y = load <256 x i32>, <256 x i32>* %1, align 1024
%add = add <256 x i32> %y, %x %add = add <256 x i32> %y, %x
ret <256 x i32> %add ret <256 x i32> %add
} }
define dso_local void @__tile_loadd(%struct.__tile_str* nocapture %0, i8* %1, i64 %2) local_unnamed_addr #0 { define dso_local void @__tile_loadd(%struct.__tile_str* nocapture %0, i8* %1, i64 %2) local_unnamed_addr {
; CHECK-LABEL: @__tile_loadd( ; CHECK-LABEL: @__tile_loadd(
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR:%.*]], %struct.__tile_str* [[TMP0:%.*]], i64 0, i32 0 ; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR:%.*]], %struct.__tile_str* [[TMP0:%.*]], i64 0, i32 0
; CHECK-NEXT: [[TMP5:%.*]] = load i16, i16* [[TMP4]], align 64, [[TBAA5]] ; CHECK-NEXT: [[TMP5:%.*]] = load i16, i16* [[TMP4]], align 64
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP0]], i64 0, i32 1 ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP0]], i64 0, i32 1
; CHECK-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2, [[TBAA8:!tbaa !.*]] ; CHECK-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; CHECK-NEXT: [[TMP8:%.*]] = shl i64 [[TMP2:%.*]], 32 ; CHECK-NEXT: [[TMP8:%.*]] = shl i64 [[TMP2:%.*]], 32
; CHECK-NEXT: [[TMP9:%.*]] = ashr exact i64 [[TMP8]], 32 ; CHECK-NEXT: [[TMP9:%.*]] = ashr exact i64 [[TMP8]], 32
; CHECK-NEXT: [[TMP10:%.*]] = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP1:%.*]], i64 [[TMP9]]) [[ATTR3]] ; CHECK-NEXT: [[TMP10:%.*]] = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP1:%.*]], i64 [[TMP9]])
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP0]], i64 0, i32 2 ; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP0]], i64 0, i32 2
; CHECK-NEXT: [[TMP12:%.*]] = bitcast <256 x i32>* [[TMP11]] to i8* ; CHECK-NEXT: [[TMP12:%.*]] = bitcast <256 x i32>* [[TMP11]] to i8*
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP12]], i64 64, x86_amx [[TMP10]]) ; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP12]], i64 64, x86_amx [[TMP10]])
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
%4 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 0 %4 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 0
%5 = load i16, i16* %4, align 64, !tbaa !2 %5 = load i16, i16* %4, align 64
%6 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 1 %6 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 1
%7 = load i16, i16* %6, align 2, !tbaa !7 %7 = load i16, i16* %6, align 2
%8 = shl i64 %2, 32 %8 = shl i64 %2, 32
%9 = ashr exact i64 %8, 32 %9 = ashr exact i64 %8, 32
%10 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %5, i16 %7, i8* %1, i64 %9) #3 %10 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %5, i16 %7, i8* %1, i64 %9)
%11 = bitcast x86_amx %10 to <256 x i32> %11 = bitcast x86_amx %10 to <256 x i32>
%12 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 2 %12 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 2
store <256 x i32> %11, <256 x i32>* %12, align 64, !tbaa !8 store <256 x i32> %11, <256 x i32>* %12, align 64
ret void ret void
} }
define dso_local void @__tile_dpbsud(%struct.__tile_str* nocapture %0, %struct.__tile_str* nocapture readonly byval(%struct.__tile_str) align 64 %1, %struct.__tile_str* nocapture readonly byval(%struct.__tile_str) align 64 %2) local_unnamed_addr #0 { define dso_local void @__tile_dpbsud(%struct.__tile_str* nocapture %0, %struct.__tile_str* nocapture readonly byval(%struct.__tile_str) align 64 %1, %struct.__tile_str* nocapture readonly byval(%struct.__tile_str) align 64 %2) local_unnamed_addr {
; CHECK-LABEL: @__tile_dpbsud( ; CHECK-LABEL: @__tile_dpbsud(
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR:%.*]], %struct.__tile_str* [[TMP1:%.*]], i64 0, i32 0 ; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR:%.*]], %struct.__tile_str* [[TMP1:%.*]], i64 0, i32 0
; CHECK-NEXT: [[TMP5:%.*]] = load i16, i16* [[TMP4]], align 64, [[TBAA5]] ; CHECK-NEXT: [[TMP5:%.*]] = load i16, i16* [[TMP4]], align 64
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2:%.*]], i64 0, i32 1 ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2:%.*]], i64 0, i32 1
; CHECK-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2, [[TBAA8]] ; CHECK-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP1]], i64 0, i32 1 ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP1]], i64 0, i32 1
; CHECK-NEXT: [[TMP9:%.*]] = load i16, i16* [[TMP8]], align 2, [[TBAA8]] ; CHECK-NEXT: [[TMP9:%.*]] = load i16, i16* [[TMP8]], align 2
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP0:%.*]], i64 0, i32 2 ; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP0:%.*]], i64 0, i32 2
; CHECK-NEXT: [[TMP11:%.*]] = bitcast <256 x i32>* [[TMP10]] to i8* ; CHECK-NEXT: [[TMP11:%.*]] = bitcast <256 x i32>* [[TMP10]] to i8*
; CHECK-NEXT: [[TMP12:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP11]], i64 64) ; CHECK-NEXT: [[TMP12:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP11]], i64 64)
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP1]], i64 0, i32 2 ; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP1]], i64 0, i32 2
; CHECK-NEXT: [[TMP14:%.*]] = bitcast <256 x i32>* [[TMP13]] to i8* ; CHECK-NEXT: [[TMP14:%.*]] = bitcast <256 x i32>* [[TMP13]] to i8*
; CHECK-NEXT: [[TMP15:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP9]], i8* [[TMP14]], i64 64) ; CHECK-NEXT: [[TMP15:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP9]], i8* [[TMP14]], i64 64)
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2]], i64 0, i32 2 ; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2]], i64 0, i32 2
; CHECK-NEXT: [[TMP17:%.*]] = bitcast <256 x i32>* [[TMP16]] to i8* ; CHECK-NEXT: [[TMP17:%.*]] = bitcast <256 x i32>* [[TMP16]] to i8*
; CHECK-NEXT: [[TMP18:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP9]], i16 [[TMP7]], i8* [[TMP17]], i64 64) ; CHECK-NEXT: [[TMP18:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP9]], i16 [[TMP7]], i8* [[TMP17]], i64 64)
; CHECK-NEXT: [[TMP19:%.*]] = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 [[TMP5]], i16 [[TMP7]], i16 [[TMP9]], x86_amx [[TMP12]], x86_amx [[TMP15]], x86_amx [[TMP18]]) [[ATTR3]] ; CHECK-NEXT: [[TMP19:%.*]] = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 [[TMP5]], i16 [[TMP7]], i16 [[TMP9]], x86_amx [[TMP12]], x86_amx [[TMP15]], x86_amx [[TMP18]])
; CHECK-NEXT: [[TMP20:%.*]] = bitcast <256 x i32>* [[TMP10]] to i8* ; CHECK-NEXT: [[TMP20:%.*]] = bitcast <256 x i32>* [[TMP10]] to i8*
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP20]], i64 64, x86_amx [[TMP19]]) ; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP20]], i64 64, x86_amx [[TMP19]])
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
%4 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %1, i64 0, i32 0 %4 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %1, i64 0, i32 0
%5 = load i16, i16* %4, align 64, !tbaa !2 %5 = load i16, i16* %4, align 64
%6 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 1 %6 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 1
%7 = load i16, i16* %6, align 2, !tbaa !7 %7 = load i16, i16* %6, align 2
%8 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %1, i64 0, i32 1 %8 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %1, i64 0, i32 1
%9 = load i16, i16* %8, align 2, !tbaa !7 %9 = load i16, i16* %8, align 2
%10 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 2 %10 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %0, i64 0, i32 2
%11 = load <256 x i32>, <256 x i32>* %10, align 64, !tbaa !8 %11 = load <256 x i32>, <256 x i32>* %10, align 64
%12 = bitcast <256 x i32> %11 to x86_amx %12 = bitcast <256 x i32> %11 to x86_amx
%13 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %1, i64 0, i32 2 %13 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %1, i64 0, i32 2
%14 = load <256 x i32>, <256 x i32>* %13, align 64, !tbaa !8 %14 = load <256 x i32>, <256 x i32>* %13, align 64
%15 = bitcast <256 x i32> %14 to x86_amx %15 = bitcast <256 x i32> %14 to x86_amx
%16 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 2 %16 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 2
%17 = load <256 x i32>, <256 x i32>* %16, align 64, !tbaa !8 %17 = load <256 x i32>, <256 x i32>* %16, align 64
%18 = bitcast <256 x i32> %17 to x86_amx %18 = bitcast <256 x i32> %17 to x86_amx
%19 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %5, i16 %7, i16 %9, x86_amx %12, x86_amx %15, x86_amx %18) #3 %19 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %5, i16 %7, i16 %9, x86_amx %12, x86_amx %15, x86_amx %18)
%20 = bitcast x86_amx %19 to <256 x i32> %20 = bitcast x86_amx %19 to <256 x i32>
store <256 x i32> %20, <256 x i32>* %10, align 64, !tbaa !8 store <256 x i32> %20, <256 x i32>* %10, align 64
ret void ret void
} }
define dso_local void @__tile_stored(i8* %0, i64 %1, %struct.__tile_str* nocapture readonly byval(%struct.__tile_str) align 64 %2) local_unnamed_addr #1 { define dso_local void @__tile_stored(i8* %0, i64 %1, %struct.__tile_str* nocapture readonly byval(%struct.__tile_str) align 64 %2) local_unnamed_addr {
; CHECK-LABEL: @__tile_stored( ; CHECK-LABEL: @__tile_stored(
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR:%.*]], %struct.__tile_str* [[TMP2:%.*]], i64 0, i32 0 ; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR:%.*]], %struct.__tile_str* [[TMP2:%.*]], i64 0, i32 0
; CHECK-NEXT: [[TMP5:%.*]] = load i16, i16* [[TMP4]], align 64, [[TBAA5]] ; CHECK-NEXT: [[TMP5:%.*]] = load i16, i16* [[TMP4]], align 64
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2]], i64 0, i32 1 ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2]], i64 0, i32 1
; CHECK-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2, [[TBAA8]] ; CHECK-NEXT: [[TMP7:%.*]] = load i16, i16* [[TMP6]], align 2
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2]], i64 0, i32 2 ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [[STRUCT___TILE_STR]], %struct.__tile_str* [[TMP2]], i64 0, i32 2
; CHECK-NEXT: [[TMP9:%.*]] = bitcast <256 x i32>* [[TMP8]] to i8* ; CHECK-NEXT: [[TMP9:%.*]] = bitcast <256 x i32>* [[TMP8]] to i8*
; CHECK-NEXT: [[TMP10:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP9]], i64 64) ; CHECK-NEXT: [[TMP10:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP9]], i64 64)
; CHECK-NEXT: [[TMP11:%.*]] = shl i64 [[TMP1:%.*]], 32 ; CHECK-NEXT: [[TMP11:%.*]] = shl i64 [[TMP1:%.*]], 32
; CHECK-NEXT: [[TMP12:%.*]] = ashr exact i64 [[TMP11]], 32 ; CHECK-NEXT: [[TMP12:%.*]] = ashr exact i64 [[TMP11]], 32
; CHECK-NEXT: tail call void @llvm.x86.tilestored64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP0:%.*]], i64 [[TMP12]], x86_amx [[TMP10]]) [[ATTR3]] ; CHECK-NEXT: tail call void @llvm.x86.tilestored64.internal(i16 [[TMP5]], i16 [[TMP7]], i8* [[TMP0:%.*]], i64 [[TMP12]], x86_amx [[TMP10]])
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
%4 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 0 %4 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 0
%5 = load i16, i16* %4, align 64, !tbaa !2 %5 = load i16, i16* %4, align 64
%6 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 1 %6 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 1
%7 = load i16, i16* %6, align 2, !tbaa !7 %7 = load i16, i16* %6, align 2
%8 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 2 %8 = getelementptr inbounds %struct.__tile_str, %struct.__tile_str* %2, i64 0, i32 2
%9 = load <256 x i32>, <256 x i32>* %8, align 64, !tbaa !8 %9 = load <256 x i32>, <256 x i32>* %8, align 64
%10 = bitcast <256 x i32> %9 to x86_amx %10 = bitcast <256 x i32> %9 to x86_amx
%11 = shl i64 %1, 32 %11 = shl i64 %1, 32
%12 = ashr exact i64 %11, 32 %12 = ashr exact i64 %11, 32
tail call void @llvm.x86.tilestored64.internal(i16 %5, i16 %7, i8* %0, i64 %12, x86_amx %10) #3 tail call void @llvm.x86.tilestored64.internal(i16 %5, i16 %7, i8* %0, i64 %12, x86_amx %10)
ret void ret void
} }
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64) #3 declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx) #3 declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx) #3 declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
attributes #0 = { alwaysinline nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="8192" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile,+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { alwaysinline nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile,+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { alwaysinline nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile,+avx,+avx2,+avx512f,+cx8,+f16c,+fma,+fxsr,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave" "tune-cpu"="generic" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #3 = { nounwind }
!llvm.module.flags = !{!0}
!llvm.ident = !{!1}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 12.0.0 (ssh://git-amr-1.devtools.intel.com:29418/dpd_icl-llvm_project_worldread f3c78a3f053379a2511e00e9ce2c13383ea3f835)"}
!2 = !{!3, !4, i64 0}
!3 = !{!"__tile_str", !4, i64 0, !4, i64 2, !5, i64 1024}
!4 = !{!"short", !5, i64 0}
!5 = !{!"omnipotent char", !6, i64 0}
!6 = !{!"Simple C/C++ TBAA"}
!7 = !{!3, !4, i64 2}
!8 = !{!5, !5, i64 0}