forked from OSchip/llvm-project
151 lines
6.4 KiB
LLVM
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()
|