derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/CodeGen/X86/AMX/amx-combine-undef.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

270 lines
11 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt --codegen-opt-level=2 -mtriple=x86_64 -x86-lower-amx-type %s -S | FileCheck %s
; RUN: opt --codegen-opt-level=2 -mtriple=x86_64 -passes=x86-lower-amx-type %s -S | FileCheck %s
define void @undef_2phi(ptr%buf) {
; CHECK-LABEL: @undef_2phi(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: br i1 poison, label [[L1:%.*]], label [[L2:%.*]]
; CHECK: l1:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: br i1 poison, label [[L2]], label [[L3:%.*]]
; CHECK: l2:
; CHECK-NEXT: [[TMP1:%.*]] = phi x86_amx [ [[TMP0]], [[ENTRY:%.*]] ], [ [[T1]], [[L1]] ]
; CHECK-NEXT: br i1 poison, label [[L3]], label [[EXIT:%.*]]
; CHECK: l3:
; CHECK-NEXT: [[TMP2:%.*]] = phi x86_amx [ [[TMP1]], [[L2]] ], [ [[T1]], [[L1]] ]
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr [[BUF:%.*]], i64 1024, x86_amx [[TMP2]])
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br i1 poison, label %l1, label %l2
l1:
%t1 = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
%t2 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t1)
br i1 poison, label %l2, label %l3
l2:
%t3 = phi <256 x i32> [ poison, %entry ], [ %t2, %l1 ]
br i1 poison, label %l3, label %exit
l3:
%t4 = phi <256 x i32> [ %t3, %l2], [ %t2, %l1 ]
%t5 = call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> %t4)
call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr %buf, i64 1024, x86_amx %t5)
br label %exit
exit:
ret void
}
define void @foo_undef(ptr%buf) {
; CHECK-LABEL: @foo_undef(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: br i1 poison, label [[L1:%.*]], label [[L2:%.*]]
; CHECK: l1:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: br i1 poison, label [[L2]], label [[EXIT:%.*]]
; CHECK: l2:
; CHECK-NEXT: [[TMP1:%.*]] = phi x86_amx [ [[TMP0]], [[ENTRY:%.*]] ], [ [[T1]], [[L1]] ]
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr [[BUF:%.*]], i64 1024, x86_amx [[TMP1]])
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br i1 poison, label %l1, label %l2
l1:
%t1 = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
%t2 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t1)
br i1 poison, label %l2, label %exit
l2:
%t3 = phi <256 x i32> [ poison, %entry ], [ %t2, %l1 ]
%t4 = call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> %t3)
call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr %buf, i64 1024, x86_amx %t4)
br label %exit
exit:
ret void
}
define void @foo_zero(ptr%buf) {
; CHECK-LABEL: @foo_zero(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: br i1 poison, label [[L1:%.*]], label [[L2:%.*]]
; CHECK: l1:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: br i1 poison, label [[L2]], label [[EXIT:%.*]]
; CHECK: l2:
; CHECK-NEXT: [[TMP1:%.*]] = phi x86_amx [ [[TMP0]], [[ENTRY:%.*]] ], [ [[T1]], [[L1]] ]
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr [[BUF:%.*]], i64 1024, x86_amx [[TMP1]])
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br i1 poison, label %l1, label %l2
l1:
%t1 = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
%t2 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t1)
br i1 poison, label %l2, label %exit
l2:
%t3 = phi <256 x i32> [ zeroinitializer, %entry ], [ %t2, %l1 ]
%t4 = call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> %t3)
call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr %buf, i64 1024, x86_amx %t4)
br label %exit
exit:
ret void
}
define void @foo_vrow(ptr%buf, i16 %row) {
; CHECK-LABEL: @foo_vrow(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: [[TMP1:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: br i1 poison, label [[L1:%.*]], label [[L2:%.*]]
; CHECK: l1:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 [[ROW:%.*]], i16 32)
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[ROW]], i16 32, ptr [[TMP1]], i64 32, x86_amx [[T1]])
; CHECK-NEXT: [[TMP3:%.*]] = load <256 x i32>, ptr [[TMP1]], align 1024
; CHECK-NEXT: br i1 poison, label [[L2]], label [[EXIT:%.*]]
; CHECK: l2:
; CHECK-NEXT: [[T3:%.*]] = phi <256 x i32> [ poison, [[ENTRY:%.*]] ], [ [[TMP3]], [[L1]] ]
; CHECK-NEXT: store <256 x i32> [[T3]], ptr [[TMP0]], align 1024
; CHECK-NEXT: [[TMP5:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 [[ROW]], i16 32, ptr [[TMP0]], i64 32)
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 [[ROW]], i16 32, ptr [[BUF:%.*]], i64 1024, x86_amx [[TMP5]])
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br i1 poison, label %l1, label %l2
l1:
%t1 = call x86_amx @llvm.x86.tilezero.internal(i16 %row, i16 32)
%t2 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t1)
br i1 poison, label %l2, label %exit
l2:
%t3 = phi <256 x i32> [ poison, %entry ], [ %t2, %l1 ]
%t4 = call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> %t3)
call void @llvm.x86.tilestored64.internal(i16 %row, i16 32, ptr %buf, i64 1024, x86_amx %t4)
br label %exit
exit:
ret void
}
define void @foo_vcol(ptr%buf, i16 %col) {
; CHECK-LABEL: @foo_vcol(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: [[TMP1:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: br i1 poison, label [[L1:%.*]], label [[L2:%.*]]
; CHECK: l1:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 [[COL:%.*]])
; CHECK-NEXT: [[TMP3:%.*]] = sext i16 [[COL]] to i64
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 [[COL]], ptr [[TMP1]], i64 [[TMP3]], x86_amx [[T1]])
; CHECK-NEXT: [[TMP4:%.*]] = load <256 x i32>, ptr [[TMP1]], align 1024
; CHECK-NEXT: br i1 poison, label [[L2]], label [[EXIT:%.*]]
; CHECK: l2:
; CHECK-NEXT: [[T3:%.*]] = phi <256 x i32> [ zeroinitializer, [[ENTRY:%.*]] ], [ [[TMP4]], [[L1]] ]
; CHECK-NEXT: store <256 x i32> [[T3]], ptr [[TMP0]], align 1024
; CHECK-NEXT: [[TMP6:%.*]] = sext i16 [[COL]] to i64
; CHECK-NEXT: [[TMP7:%.*]] = call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 [[COL]], ptr [[TMP0]], i64 [[TMP6]])
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 [[COL]], ptr [[BUF:%.*]], i64 1024, x86_amx [[TMP7]])
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br i1 poison, label %l1, label %l2
l1:
%t1 = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 %col)
%t2 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t1)
br i1 poison, label %l2, label %exit
l2:
%t3 = phi <256 x i32> [ zeroinitializer, %entry ], [ %t2, %l1 ]
%t4 = call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> %t3)
call void @llvm.x86.tilestored64.internal(i16 8, i16 %col, ptr %buf, i64 1024, x86_amx %t4)
br label %exit
exit:
ret void
}
define void @noshape(ptr%buf) {
; CHECK-LABEL: @noshape(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: br i1 poison, label [[L1:%.*]], label [[L2:%.*]]
; CHECK: l1:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr [[TMP0]], i64 32, x86_amx [[T1]])
; CHECK-NEXT: [[TMP2:%.*]] = load <256 x i32>, ptr [[TMP0]], align 1024
; CHECK-NEXT: br i1 poison, label [[L2]], label [[EXIT:%.*]]
; CHECK: l2:
; CHECK-NEXT: [[T3:%.*]] = phi <256 x i32> [ poison, [[ENTRY:%.*]] ], [ [[TMP2]], [[L1]] ]
; CHECK-NEXT: store <256 x i32> [[T3]], ptr [[BUF:%.*]], align 1024
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br i1 poison, label %l1, label %l2
l1:
%t1 = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
%t2 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t1)
br i1 poison, label %l2, label %exit
l2:
%t3 = phi <256 x i32> [ poison, %entry ], [ %t2, %l1 ]
%t4 = call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> %t3)
%t5 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t4)
store <256 x i32> %t5, ptr %buf
br label %exit
exit:
ret void
}
define void @noshape2(ptr%buf) {
; CHECK-LABEL: @noshape2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = alloca <256 x i32>, align 64
; CHECK-NEXT: br i1 poison, label [[L1:%.*]], label [[L2:%.*]]
; CHECK: l1:
; CHECK-NEXT: [[T1:%.*]] = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 32, ptr [[TMP0]], i64 32, x86_amx [[T1]])
; CHECK-NEXT: [[TMP2:%.*]] = load <256 x i32>, ptr [[TMP0]], align 1024
; CHECK-NEXT: br i1 poison, label [[L2]], label [[EXIT:%.*]]
; CHECK: l2:
; CHECK-NEXT: [[T3:%.*]] = phi <256 x i32> [ poison, [[ENTRY:%.*]] ], [ [[TMP2]], [[L1]] ]
; CHECK-NEXT: [[T6:%.*]] = call <256 x i32> @llvm.abs.v256i32(<256 x i32> [[T3]], i1 true)
; CHECK-NEXT: store <256 x i32> [[T6]], ptr [[BUF:%.*]], align 1024
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br i1 poison, label %l1, label %l2
l1:
%t1 = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 32)
%t2 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t1)
br i1 poison, label %l2, label %exit
l2:
%t3 = phi <256 x i32> [ poison, %entry ], [ %t2, %l1 ]
%t4 = call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> %t3)
%t5 = call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx %t4)
%t6 = call <256 x i32> @llvm.abs.v256i32(<256 x i32> %t5, i1 1)
store <256 x i32> %t6, ptr %buf
br label %exit
exit:
ret void
}
declare <256 x i32> @llvm.abs.v256i32(<256 x i32>, i1)
declare x86_amx @llvm.x86.tilezero.internal(i16, i16)
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, ptr, i64)
declare <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx)
declare x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32>)
declare void @llvm.x86.tilestored64.internal(i16, i16, ptr, i64, x86_amx)
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
Reference in new issue View Git Blame Copy Permalink