RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 02:33:06 +01:00
Code Issues Projects Releases Wiki Activity

[X86][AMX] Add test case for combining AMX bitcast.

Browse Source
This commit is contained in:
Luo, Yuanke 2021-03-09 19:46:00 +08:00
parent c05fa040af
commit d4f790f4bb
1 changed files with 65 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
test/Transforms/InstCombine/X86/x86-amx.ll Normal file
View File

@ -0,0 +1,65 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -instcombine -S < %s | FileCheck %s
; RUN: opt -passes=instcombine -S < %s | FileCheck %s
define linkonce_odr dso_local void @foo(<256 x i32>* %arrayidx16, <256 x i32>* %arrayidx29, <256 x i32>* %arrayidx35) local_unnamed_addr {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_COND9:%.*]]
; CHECK: for.cond9:
; CHECK-NEXT: br i1 undef, label [[FOR_BODY14:%.*]], label [[EXIT:%.*]]
; CHECK: for.body14:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast <256 x i32>* [[ARRAYIDX16:%.*]] to x86_amx*
; CHECK-NEXT: [[T51:%.*]] = load x86_amx, x86_amx* [[TMP0]], align 64
; CHECK-NEXT: br label [[FOR_COND18:%.*]]
; CHECK: for.cond18:
; CHECK-NEXT: [[TMP1:%.*]] = phi x86_amx [ [[T51]], [[FOR_BODY14]] ], [ [[T11:%.*]], [[FOR_BODY24:%.*]] ]
; CHECK-NEXT: br i1 undef, label [[FOR_BODY24]], label [[FOR_COND_CLEANUP23:%.*]]
; CHECK: for.cond.cleanup23:
; CHECK-NEXT: [[TMP2:%.*]] = bitcast x86_amx [[TMP1]] to <256 x i32>
; CHECK-NEXT: store <256 x i32> [[TMP2]], <256 x i32>* [[ARRAYIDX16]], align 64
; CHECK-NEXT: br label [[FOR_COND9]]
; CHECK: for.body24:
; CHECK-NEXT: [[T6:%.*]] = load <256 x i32>, <256 x i32>* [[ARRAYIDX29:%.*]], align 64
; CHECK-NEXT: [[T7:%.*]] = load <256 x i32>, <256 x i32>* [[ARRAYIDX35:%.*]], align 64
; CHECK-NEXT: [[T9:%.*]] = bitcast <256 x i32> [[T6]] to x86_amx
; CHECK-NEXT: [[T10:%.*]] = bitcast <256 x i32> [[T7]] to x86_amx
; CHECK-NEXT: [[T11]] = call x86_amx @llvm.x86.tdpbssd.internal(i16 1, i16 4, i16 4, x86_amx [[TMP1]], x86_amx [[T9]], x86_amx [[T10]])
; CHECK-NEXT: br label [[FOR_COND18]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %for.cond9
for.cond9: ; preds = %for.cond, %for.cond.cleanup23
br i1 undef, label %for.body14, label %exit
for.body14:
%t5 = load <256 x i32>, <256 x i32>* %arrayidx16, align 64
br label %for.cond18
for.cond18: ; preds = %for.body24, %for.body14
%sub_c.sroa.0.0 = phi <256 x i32> [ %t5, %for.body14 ], [ %t12, %for.body24 ]
br i1 undef, label %for.body24, label %for.cond.cleanup23
for.cond.cleanup23: ; preds = %for.cond18
store <256 x i32> %sub_c.sroa.0.0, <256 x i32>* %arrayidx16, align 64
br label %for.cond9
for.body24: ; preds = %for.cond18
%t6 = load <256 x i32>, <256 x i32>* %arrayidx29, align 64
%t7 = load <256 x i32>, <256 x i32>* %arrayidx35, align 64
%t8 = bitcast <256 x i32> %sub_c.sroa.0.0 to x86_amx
%t9 = bitcast <256 x i32> %t6 to x86_amx
%t10 = bitcast <256 x i32> %t7 to x86_amx
%t11 = call x86_amx @llvm.x86.tdpbssd.internal(i16 1, i16 4, i16 4, x86_amx %t8, x86_amx %t9, x86_amx %t10) #12
%t12 = bitcast x86_amx %t11 to <256 x i32>
br label %for.cond18
exit:
ret void
}
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)
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)