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
178 lines
7.8 KiB
LLVM
178 lines
7.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -O0 -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f | FileCheck %s --check-prefix=AVX512
|
|
|
|
@buf = 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 %cond, i16 signext %row, i16 signext %col) nounwind {
|
|
; AVX512-LABEL: test_api:
|
|
; AVX512: # %bb.0: # %entry
|
|
; AVX512-NEXT: pushq %rbp
|
|
; AVX512-NEXT: movq %rsp, %rbp
|
|
; AVX512-NEXT: andq $-1024, %rsp # imm = 0xFC00
|
|
; AVX512-NEXT: subq $8192, %rsp # imm = 0x2000
|
|
; AVX512-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovups %zmm0, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movb $1, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %dx, %ax
|
|
; AVX512-NEXT: movw %ax, {{[-0-9]+}}(%r{{[sb]}}p) # 2-byte Spill
|
|
; AVX512-NEXT: movw %si, %ax
|
|
; AVX512-NEXT: movw %ax, {{[-0-9]+}}(%r{{[sb]}}p) # 2-byte Spill
|
|
; AVX512-NEXT: cmpl $0, %edi
|
|
; AVX512-NEXT: je .LBB0_2
|
|
; AVX512-NEXT: # %bb.1: # %if.then
|
|
; AVX512-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %ax # 2-byte Reload
|
|
; AVX512-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %cx # 2-byte Reload
|
|
; AVX512-NEXT: movl $buf, %esi
|
|
; AVX512-NEXT: movl $32, %edi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %dx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: ldtilecfg {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: tileloadd (%rsi,%rdi), %tmm0
|
|
; AVX512-NEXT: movl $64, %edi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rsi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: tilestored %tmm0, (%rsi,%rdi)
|
|
; AVX512-NEXT: movl $buf, %esi
|
|
; AVX512-NEXT: movl $32, %edi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: # implicit-def: $dl
|
|
; AVX512-NEXT: movb %dl, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: ldtilecfg {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: tileloadd (%rsi,%rdi), %tmm0
|
|
; AVX512-NEXT: movl $64, %edi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rsi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: tilestored %tmm0, (%rsi,%rdi)
|
|
; AVX512-NEXT: movl $buf, %edx
|
|
; AVX512-NEXT: movl $32, %esi
|
|
; AVX512-NEXT: tileloadd (%rdx,%rsi), %tmm0
|
|
; AVX512-NEXT: movl $64, %esi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX512-NEXT: tilestored %tmm0, (%rdx,%rsi)
|
|
; AVX512-NEXT: jmp .LBB0_3
|
|
; AVX512-NEXT: .LBB0_2: # %if.else
|
|
; AVX512-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %ax # 2-byte Reload
|
|
; AVX512-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %cx # 2-byte Reload
|
|
; AVX512-NEXT: movl $buf2, %esi
|
|
; AVX512-NEXT: movl $32, %edi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %dx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: ldtilecfg {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: tileloadd (%rsi,%rdi), %tmm0
|
|
; AVX512-NEXT: movl $64, %edi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rsi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: tilestored %tmm0, (%rsi,%rdi)
|
|
; AVX512-NEXT: movl $buf2, %esi
|
|
; AVX512-NEXT: movl $32, %edi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: # implicit-def: $dl
|
|
; AVX512-NEXT: movb %dl, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: ldtilecfg {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: tileloadd (%rsi,%rdi), %tmm0
|
|
; AVX512-NEXT: movl $64, %edi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rsi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: tilestored %tmm0, (%rsi,%rdi)
|
|
; AVX512-NEXT: movl $buf2, %edx
|
|
; AVX512-NEXT: movl $32, %esi
|
|
; AVX512-NEXT: tileloadd (%rdx,%rsi), %tmm0
|
|
; AVX512-NEXT: movl $64, %esi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX512-NEXT: tilestored %tmm0, (%rdx,%rsi)
|
|
; AVX512-NEXT: .LBB0_3: # %if.end
|
|
; AVX512-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %ax # 2-byte Reload
|
|
; AVX512-NEXT: movw {{[-0-9]+}}(%r{{[sb]}}p), %cx # 2-byte Reload
|
|
; AVX512-NEXT: movl $64, %edi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX512-NEXT: movw $8, %si
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %si, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: ldtilecfg {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: tileloadd (%rdx,%rdi), %tmm0
|
|
; AVX512-NEXT: movabsq $64, %rdx
|
|
; AVX512-NEXT: tilestored %tmm0, 1024(%rsp,%rdx) # 1024-byte Folded Spill
|
|
; AVX512-NEXT: movl $64, %r8d
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %si, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: # implicit-def: $al
|
|
; AVX512-NEXT: movb %al, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: # implicit-def: $dl
|
|
; AVX512-NEXT: movb %dl, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: movw %cx, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: ldtilecfg {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: tileloadd (%rdi,%r8), %tmm2
|
|
; AVX512-NEXT: movl $64, %edi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX512-NEXT: tileloadd (%rdx,%rdi), %tmm0
|
|
; AVX512-NEXT: movw $8, %dx
|
|
; AVX512-NEXT: movabsq $64, %rdi
|
|
; AVX512-NEXT: tileloadd 1024(%rsp,%rdi), %tmm1 # 1024-byte Folded Reload
|
|
; AVX512-NEXT: tdpbssd %tmm2, %tmm1, %tmm0
|
|
; AVX512-NEXT: movl $64, %esi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX512-NEXT: tilestored %tmm0, (%rdx,%rsi)
|
|
; AVX512-NEXT: movl $64, %esi
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX512-NEXT: tileloadd (%rdx,%rsi), %tmm0
|
|
; AVX512-NEXT: movl $buf, %edx
|
|
; AVX512-NEXT: movl $32, %esi
|
|
; AVX512-NEXT: tilestored %tmm0, (%rdx,%rsi)
|
|
; AVX512-NEXT: movq %rbp, %rsp
|
|
; AVX512-NEXT: popq %rbp
|
|
; AVX512-NEXT: tilerelease
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
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
|
|
}
|
|
|
|
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, ptr, 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, ptr, i64, x86_amx)
|