derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
76 lines
4.9 KiB
LLVM
76 lines
4.9 KiB
LLVM
; RUN: opt < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -x86-lower-amx-type -S | FileCheck %s
|
|
; RUN: opt < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -passes=x86-lower-amx-type -S | FileCheck %s
|
|
|
|
@buf = dso_local global [1024 x i8] zeroinitializer, align 16
|
|
@buf2 = dso_local global [1024 x i8] zeroinitializer, align 16
|
|
|
|
; Function Attrs: nounwind uwtable
|
|
define dso_local void @test_api(i32 %cond, i16 signext %row, i16 signext %col) local_unnamed_addr {
|
|
|
|
; CHECK-LABEL: entry:
|
|
; CHECK: %{{[0-9]+}} = alloca <256 x i32>, align 1024
|
|
; CHECK-NEXT: %{{[0-9]+}} = alloca <256 x i32>, align 1024
|
|
; CHECK-NEXT: %{{[0-9]+}} = alloca <256 x i32>, align 1024
|
|
; CHECK-NEXT: %{{[0-9]+}} = alloca <256 x i32>, align 1024
|
|
; CHECK-NEXT: %tobool.not = icmp eq i32 %cond, 0
|
|
; CHECK-NEXT: br i1 %tobool.not, label %if.else, label %if.then
|
|
; CHECK: if.then:
|
|
; CHECK-NEXT: %{{[0-9]+}} = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 8, ptr @buf, i64 32)
|
|
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 %row, i16 8, ptr %{{[0-9]+}}, i64 64, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: %{{[0-9]+}} = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %col, ptr @buf, i64 32)
|
|
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 %col, ptr %{{[0-9]+}}, i64 64, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: %{{[0-9]+}} = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 %col, ptr @buf, i64 32)
|
|
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 %row, i16 %col, ptr %{{[0-9]+}}, i64 64, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: br label %if.end
|
|
; CHECK: if.else:
|
|
; CHECK-NEXT: %{{[0-9]+}} = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 8, ptr @buf2, i64 32)
|
|
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 %row, i16 8, ptr %{{[0-9]+}}, i64 64, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: %{{[0-9]+}} = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %col, ptr @buf2, i64 32)
|
|
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 8, i16 %col, ptr %{{[0-9]+}}, i64 64, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: %{{[0-9]+}} = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 %col, ptr @buf2, i64 32)
|
|
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 %row, i16 %col, ptr %{{[0-9]+}}, i64 64, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: br label %if.end
|
|
; CHECK: if.end:
|
|
; CHECK-NEXT: %{{[0-9]+}} = call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 8, ptr %{{[0-9]+}}, i64 64)
|
|
; CHECK-NEXT: %{{[0-9]+}} = call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %col, ptr %{{[0-9]+}}, i64 64)
|
|
; CHECK-NEXT: %{{[0-9]+}} = call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 %col, ptr %{{[0-9]+}}, i64 64)
|
|
; CHECK-NEXT: %{{[0-9]+}} = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %row, i16 %col, i16 8, x86_amx %{{[0-9]+}}, x86_amx %{{[0-9]+}}, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: call void @llvm.x86.tilestored64.internal(i16 %row, i16 %col, ptr %{{[0-9]+}}, i64 64, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: %{{[0-9]+}} = call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 %col, ptr %{{[0-9]+}}, i64 64)
|
|
; CHECK-NEXT: tail call void @llvm.x86.tilestored64.internal(i16 %row, i16 %col, ptr @buf, i64 32, x86_amx %{{[0-9]+}})
|
|
; CHECK-NEXT: ret void
|
|
|
|
entry:
|
|
%tobool.not = icmp eq i32 %cond, 0
|
|
br i1 %tobool.not, label %if.else, label %if.then
|
|
|
|
if.then: ; preds = %entry
|
|
%0 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 8, ptr @buf, i64 32)
|
|
%1 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %col, ptr @buf, i64 32)
|
|
%2 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 %col, ptr @buf, i64 32)
|
|
br label %if.end
|
|
|
|
if.else: ; preds = %entry
|
|
%3 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 8, ptr @buf2, i64 32)
|
|
%4 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %col, ptr @buf2, i64 32)
|
|
%5 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %row, i16 %col, ptr @buf2, i64 32)
|
|
br label %if.end
|
|
|
|
if.end: ; preds = %if.else, %if.then
|
|
%a.sroa.1094.0.in = phi x86_amx [ %3, %if.else ], [ %0, %if.then ]
|
|
%b.sroa.1069.0.in = phi x86_amx [ %4, %if.else ], [ %1, %if.then ]
|
|
%c.sroa.1044.0.in = phi x86_amx [ %5, %if.else ], [ %2, %if.then ]
|
|
%6 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %row, i16 %col, i16 8, x86_amx %c.sroa.1044.0.in, x86_amx %a.sroa.1094.0.in, x86_amx %b.sroa.1069.0.in)
|
|
tail call void @llvm.x86.tilestored64.internal(i16 %row, i16 %col, ptr @buf, i64 32, x86_amx %6)
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nounwind
|
|
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, ptr, i64)
|
|
|
|
; Function Attrs: nounwind
|
|
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.x86.tilestored64.internal(i16, i16, ptr, i64, x86_amx)
|