Displaying 2 results from an estimated 2 matches for "kxnorw".
2017 Jul 01
2
KNL Assembly Code for Matrix Multiplication
...>>>> vpbroadcastq zmm3, rsi
>>>>> add rsi, 3856000
>>>>> vpbroadcastq zmm4, qword ptr [rip + .LCPI0_3]
>>>>> vpbroadcastq zmm5, qword ptr [rip + .LCPI0_4]
>>>>> vpbroadcastq zmm6, qword ptr [rip + .LCPI0_5]
>>>>> kxnorw k1, k0, k0
>>>>> kshiftrw k1, k1, 8
>>>>> vpbroadcastq zmm7, qword ptr [rip + .LCPI0_6]
>>>>> .p2align 4, 0x90
>>>>> .LBB0_1: # %.preheader26
>>>>> # =&g...
2017 Jan 24
7
[X86][AVX512] RFC: make i1 illegal in the Codegen
...<8 x i32>%a, <8 x i32*> %p) {
%r = call <8 x i32> @llvm.masked.gather.v8i32(<8 x i32*> %p, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
ret 8 x i32>%r
}
Can be lowered to
# BB#0:
kxnorw %k0, %k0, %k1
vpgatherqd (,%zmm1), %ymm0 {%k1}
retq
Legal vectors of i1's require support for BUILD_VECTOR(i1, i1, .., i1), i1 EXTRACT_VEC_ELEMENT (...) and INSERT_VEC_ELEMENT(i1, ...) , so making i1 legal seemed like a sensible decision, and this is the current state in the top of...