llvm/llvm-project
在 GitHub 查看[X86] Failure to fold or disjoint nodes into a AVX512 predicated add instruction
Open
#164,161 创建于 2025年10月19日
backend:X86good first issuemissed-optimization
仓库指标
- Star
- (26,378 star)
- PR 合并指标
- (平均合并 1天 2小时) (30 天内合并 1,000 个 PR)
描述
https://gcc.godbolt.org/z/63scvzTGT
define <64 x i8> @select_add(<64 x i8> %0, <64 x i8> %1) {
%add0 = add <64 x i8> %0, <i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65>
%add1 = add <64 x i8> %1, <i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32>
%icmp = icmp ult <64 x i8> %add0, <i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26>
%res = select <64 x i1> %icmp, <64 x i8> %add1, <64 x i8> %add0
ret <64 x i8> %res
}
define <64 x i8> @select_or(<64 x i8> %0, <64 x i8> %1) {
%add0 = add <64 x i8> %0, <i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65, i8 -65>
%add1 = or disjoint <64 x i8> %1, <i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32, i8 32>
%icmp = icmp ult <64 x i8> %add0, <i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26, i8 26>
%res = select <64 x i1> %icmp, <64 x i8> %add1, <64 x i8> %add0
ret <64 x i8> %res
}
While the select_add case correctly folds an add into a predicated instruction:
select_add: # @select_add
vpaddb .LCPI0_0(%rip), %zmm0, %zmm0
vpcmpltub .LCPI0_1(%rip), %zmm0, %k1
vpaddb .LCPI0_2(%rip), %zmm1, %zmm0 {%k1}
retq
Using an add-like or-disjoint node fails to fold into the same add predicated instruction:
select_or: # @select_or
vpaddb .LCPI1_0(%rip), %zmm0, %zmm0
vpord .LCPI1_3(%rip){1to16}, %zmm1, %zmm1
vpcmpltub .LCPI1_2(%rip), %zmm0, %k1
vmovdqu8 %zmm1, %zmm0 {%k1}
retq