llvm-project/llvm/test/CodeGen/X86/vp2intersect_multiple_pairs.ll

151 lines
6.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512vp2intersect -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vp2intersect -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,X64
; Test with more than four live mask pairs
define void @test(<16 x i32> %a0, <16 x i32> %b0,
<16 x i32> %a1, <16 x i32> %b1,
<16 x i32> %a2, <16 x i32> %b2,
<16 x i32> %a3, <16 x i32> %b3,
<16 x i32> %a4, <16 x i32> %b4,
i16* nocapture %m0, i16* nocapture %m1) {
; X86-LABEL: test:
; X86: # %bb.0: # %entry
; X86-NEXT: pushl %ebp
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %ebp, -8
; X86-NEXT: movl %esp, %ebp
; X86-NEXT: .cfi_def_cfa_register %ebp
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: andl $-64, %esp
; X86-NEXT: subl $64, %esp
; X86-NEXT: .cfi_offset %esi, -16
; X86-NEXT: .cfi_offset %edi, -12
; X86-NEXT: movl 456(%ebp), %esi
; X86-NEXT: vmovaps 328(%ebp), %zmm3
; X86-NEXT: vmovaps 200(%ebp), %zmm4
; X86-NEXT: vmovaps 72(%ebp), %zmm5
; X86-NEXT: vp2intersectd %zmm1, %zmm0, %k0
; X86-NEXT: kmovw %k0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-NEXT: kmovw %k1, {{[0-9]+}}(%esp)
; X86-NEXT: vp2intersectd 8(%ebp), %zmm2, %k0
; X86-NEXT: kmovw %k0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-NEXT: kmovw %k1, {{[0-9]+}}(%esp)
; X86-NEXT: vp2intersectd 136(%ebp), %zmm5, %k0
; X86-NEXT: kmovw %k0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-NEXT: kmovw %k1, {{[0-9]+}}(%esp)
; X86-NEXT: vp2intersectd 264(%ebp), %zmm4, %k0
; X86-NEXT: kmovw %k0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-NEXT: kmovw %k1, {{[0-9]+}}(%esp)
; X86-NEXT: vp2intersectd 392(%ebp), %zmm3, %k0
; X86-NEXT: kmovw %k0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-NEXT: kmovw %k1, {{[0-9]+}}(%esp)
; X86-NEXT: vzeroupper
; X86-NEXT: calll dummy
; X86-NEXT: kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k0 # 4-byte Folded Reload
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: kmovw %k0, %eax
; X86-NEXT: kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k0 # 4-byte Folded Reload
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: kmovw %k0, %ecx
; X86-NEXT: kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k0 # 4-byte Folded Reload
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: kmovw %k0, %edx
; X86-NEXT: kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k0 # 4-byte Folded Reload
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: kmovw %k0, %edi
; X86-NEXT: addl %edi, %eax
; X86-NEXT: kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k2 # 4-byte Folded Reload
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k3
; X86-NEXT: kmovw %k2, %edi
; X86-NEXT: addl %ecx, %edx
; X86-NEXT: kmovw %k1, %ecx
;
; X64-LABEL: test:
; X64: # %bb.0: # %entry
; X64-NEXT: pushq %rbp
; X64-NEXT: .cfi_def_cfa_offset 16
; X64-NEXT: .cfi_offset %rbp, -16
; X64-NEXT: movq %rsp, %rbp
; X64-NEXT: .cfi_def_cfa_register %rbp
; X64-NEXT: pushq %r14
; X64-NEXT: pushq %rbx
; X64-NEXT: andq $-64, %rsp
; X64-NEXT: subq $64, %rsp
; X64-NEXT: .cfi_offset %rbx, -32
; X64-NEXT: .cfi_offset %r14, -24
; X64-NEXT: movq %rdi, %r14
; X64-NEXT: vmovaps 16(%rbp), %zmm8
; X64-NEXT: vp2intersectd %zmm1, %zmm0, %k0
; X64-NEXT: kmovw %k0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Folded Spill
; X64-NEXT: kmovw %k1, {{[0-9]+}}(%rsp)
; X64-NEXT: vp2intersectd %zmm3, %zmm2, %k0
; X64-NEXT: kmovw %k0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Folded Spill
; X64-NEXT: kmovw %k1, {{[0-9]+}}(%rsp)
; X64-NEXT: vp2intersectd %zmm5, %zmm4, %k0
; X64-NEXT: kmovw %k0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Folded Spill
; X64-NEXT: kmovw %k1, {{[0-9]+}}(%rsp)
; X64-NEXT: vp2intersectd %zmm7, %zmm6, %k0
; X64-NEXT: kmovw %k0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Folded Spill
; X64-NEXT: kmovw %k1, {{[0-9]+}}(%rsp)
; X64-NEXT: vp2intersectd 80(%rbp), %zmm8, %k0
; X64-NEXT: kmovw %k0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Folded Spill
; X64-NEXT: kmovw %k1, {{[0-9]+}}(%rsp)
; X64-NEXT: vzeroupper
; X64-NEXT: callq dummy
; X64-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k0 # 4-byte Folded Reload
; X64-NEXT: kmovw {{[0-9]+}}(%rsp), %k1
; X64-NEXT: kmovw %k0, %eax
; X64-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k0 # 4-byte Folded Reload
; X64-NEXT: kmovw {{[0-9]+}}(%rsp), %k1
; X64-NEXT: kmovw %k0, %ecx
; X64-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k0 # 4-byte Folded Reload
; X64-NEXT: kmovw {{[0-9]+}}(%rsp), %k1
; X64-NEXT: kmovw %k0, %edx
; X64-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k0 # 4-byte Folded Reload
; X64-NEXT: kmovw {{[0-9]+}}(%rsp), %k1
; X64-NEXT: kmovw %k0, %esi
; X64-NEXT: kmovw {{[-0-9]+}}(%r{{[sb]}}p), %k0 # 4-byte Folded Reload
; X64-NEXT: kmovw {{[0-9]+}}(%rsp), %k1
; X64-NEXT: kmovw %k0, %edi
; X64-NEXT: kmovw %k1, %ebx
entry:
%0 = call { <16 x i1>, <16 x i1> } @llvm.x86.avx512.vp2intersect.d.512(<16 x i32> %a0, <16 x i32> %b0)
%1 = call { <16 x i1>, <16 x i1> } @llvm.x86.avx512.vp2intersect.d.512(<16 x i32> %a1, <16 x i32> %b1)
%2 = call { <16 x i1>, <16 x i1> } @llvm.x86.avx512.vp2intersect.d.512(<16 x i32> %a2, <16 x i32> %b2)
%3 = call { <16 x i1>, <16 x i1> } @llvm.x86.avx512.vp2intersect.d.512(<16 x i32> %a3, <16 x i32> %b3)
%4 = call { <16 x i1>, <16 x i1> } @llvm.x86.avx512.vp2intersect.d.512(<16 x i32> %a4, <16 x i32> %b4)
%5 = extractvalue { <16 x i1>, <16 x i1> } %0, 0
%6 = extractvalue { <16 x i1>, <16 x i1> } %1, 0
%7 = extractvalue { <16 x i1>, <16 x i1> } %2, 0
%8 = extractvalue { <16 x i1>, <16 x i1> } %3, 0
%9 = extractvalue { <16 x i1>, <16 x i1> } %4, 0
%10 = extractvalue { <16 x i1>, <16 x i1> } %0, 1
%11 = extractvalue { <16 x i1>, <16 x i1> } %1, 1
call void @dummy()
%12 = bitcast <16 x i1> %5 to i16
%13 = bitcast <16 x i1> %6 to i16
%14 = bitcast <16 x i1> %7 to i16
%15 = bitcast <16 x i1> %8 to i16
%16 = bitcast <16 x i1> %9 to i16
%17 = bitcast <16 x i1> %10 to i16
%18 = bitcast <16 x i1> %11 to i16
%19 = add i16 %12, %13
%20 = add i16 %14, %15
%21 = add i16 %16, %17
%22 = add i16 %19, %21
%23 = add i16 %22, %20
store i16 %23, i16* %m0, align 16
ret void
}
declare { <16 x i1>, <16 x i1> } @llvm.x86.avx512.vp2intersect.d.512(<16 x i32>, <16 x i32>)
declare void @dummy()