forked from OSchip/llvm-project
[NFC][X86][Codegen] Add missing interleaving tests after D111546
This commit is contained in:
Roman Lebedev
parent
939a808670
commit
bfe5b1b312
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -713,3 +713,780 @@ define void @load_i32_stride3_vf16(<48 x i32>* %in.vec, <16 x i32>* %out.vec0, <
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @load_i32_stride3_vf32(<96 x i32>* %in.vec, <32 x i32>* %out.vec0, <32 x i32>* %out.vec1, <32 x i32>* %out.vec2) nounwind {
|
||||
; SSE-LABEL: load_i32_stride3_vf32:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $360, %rsp # imm = 0x168
|
||||
; SSE-NEXT: movaps 336(%rdi), %xmm11
|
||||
; SSE-NEXT: movaps 368(%rdi), %xmm14
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 352(%rdi), %xmm13
|
||||
; SSE-NEXT: movaps 240(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps 272(%rdi), %xmm6
|
||||
; SSE-NEXT: movaps 256(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 144(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps 176(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 160(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm8
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps %xmm9, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm8[1,1]
|
||||
; SSE-NEXT: movaps %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm5, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm7, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm3[1,1]
|
||||
; SSE-NEXT: movaps %xmm3, %xmm5
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm10, %xmm2
|
||||
; SSE-NEXT: movaps %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm1, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm6[1,1]
|
||||
; SSE-NEXT: movaps %xmm6, %xmm15
|
||||
; SSE-NEXT: movaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm12, %xmm2
|
||||
; SSE-NEXT: movaps %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm13, %xmm2
|
||||
; SSE-NEXT: movaps %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm13, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm14[1,1]
|
||||
; SSE-NEXT: movaps %xmm11, %xmm1
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm11, %xmm3
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm4
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm4, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm3[1,1]
|
||||
; SSE-NEXT: movaps (%rdi), %xmm11
|
||||
; SSE-NEXT: movaps %xmm11, %xmm3
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 128(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps %xmm7, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm3[1,1]
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm6
|
||||
; SSE-NEXT: movaps %xmm6, %xmm3
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 224(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 208(%rdi), %xmm13
|
||||
; SSE-NEXT: movaps %xmm13, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm3[1,1]
|
||||
; SSE-NEXT: movaps 192(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 320(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 304(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm3[1,1]
|
||||
; SSE-NEXT: movaps %xmm3, %xmm14
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 288(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm3, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm9, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm8 = xmm8[2,1],xmm9[3,3]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,0],xmm9[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2],xmm8[2,0]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm5, %xmm0
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm5 # 16-byte Reload
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,1],xmm5[3,3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm10 = xmm10[1,0],xmm5[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm10 = xmm10[0,2],xmm0[2,0]
|
||||
; SSE-NEXT: movaps %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm15, %xmm0
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,1],xmm3[3,3]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm15
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm15 = xmm15[1,0],xmm3[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm15 = xmm15[0,2],xmm0[2,0]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,1],xmm2[3,3]
|
||||
; SSE-NEXT: movaps %xmm1, %xmm12
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm12 = xmm12[1,0],xmm2[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm12 = xmm12[0,2],xmm0[2,0]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm8, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,1],xmm7[3,3]
|
||||
; SSE-NEXT: movaps %xmm6, %xmm1
|
||||
; SSE-NEXT: movaps %xmm6, %xmm10
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm10 = xmm10[1,0],xmm7[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm10 = xmm10[0,2],xmm0[2,0]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,1],xmm13[3,3]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[1,0],xmm13[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,2],xmm0[2,0]
|
||||
; SSE-NEXT: movaps %xmm14, %xmm2
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm5 # 16-byte Reload
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[2,1],xmm5[3,3]
|
||||
; SSE-NEXT: movaps (%rsp), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, %xmm3
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,0],xmm5[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2],xmm2[2,0]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, %xmm14
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm14 = xmm14[2,1],xmm4[3,3]
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm9 = xmm11[2,3,2,3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm11 = xmm11[1,0],xmm4[0,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm11 = xmm11[0,2],xmm14[2,0]
|
||||
; SSE-NEXT: pshufd $85, {{[-0-9]+}}(%r{{[sb]}}p), %xmm14 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm14 = mem[1,1,1,1]
|
||||
; SSE-NEXT: pshufd $238, {{[-0-9]+}}(%r{{[sb]}}p), %xmm5 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm5 = mem[2,3,2,3]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm14[0],xmm5[1],xmm14[1]
|
||||
; SSE-NEXT: shufps $196, {{[-0-9]+}}(%r{{[sb]}}p), %xmm5 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm5 = xmm5[0,1],mem[0,3]
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,1,1]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm9 = xmm9[0],xmm4[0],xmm9[1],xmm4[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,1],xmm2[0,3]
|
||||
; SSE-NEXT: pshufd $85, {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm4 = mem[1,1,1,1]
|
||||
; SSE-NEXT: pshufd $238, {{[-0-9]+}}(%r{{[sb]}}p), %xmm13 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm13 = mem[2,3,2,3]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm13 = xmm13[0],xmm4[0],xmm13[1],xmm4[1]
|
||||
; SSE-NEXT: shufps $196, {{[-0-9]+}}(%r{{[sb]}}p), %xmm13 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm13 = xmm13[0,1],mem[0,3]
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,1,1]
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm14 = xmm1[2,3,2,3]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm14 = xmm14[0],xmm4[0],xmm14[1],xmm4[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm14 = xmm14[0,1],xmm8[0,3]
|
||||
; SSE-NEXT: pshufd $85, {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm7 = mem[1,1,1,1]
|
||||
; SSE-NEXT: pshufd $238, {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm4 = mem[2,3,2,3]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1]
|
||||
; SSE-NEXT: shufps $196, {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm4 = xmm4[0,1],mem[0,3]
|
||||
; SSE-NEXT: pshufd $85, {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm8 = mem[1,1,1,1]
|
||||
; SSE-NEXT: pshufd $238, {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm7 = mem[2,3,2,3]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm8[0],xmm7[1],xmm8[1]
|
||||
; SSE-NEXT: shufps $196, {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm7 = xmm7[0,1],mem[0,3]
|
||||
; SSE-NEXT: pshufd $85, {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm8 = mem[1,1,1,1]
|
||||
; SSE-NEXT: pshufd $238, {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm1 = mem[2,3,2,3]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm8[0],xmm1[1],xmm8[1]
|
||||
; SSE-NEXT: shufps $196, {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm1 = xmm1[0,1],mem[0,3]
|
||||
; SSE-NEXT: pshufd $85, {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm8 = mem[1,1,1,1]
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1]
|
||||
; SSE-NEXT: shufps $196, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm0 = xmm0[0,1],mem[0,3]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 96(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 64(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 32(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, (%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 112(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 80(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 48(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 16(%rsi)
|
||||
; SSE-NEXT: movaps %xmm3, 96(%rdx)
|
||||
; SSE-NEXT: movaps %xmm6, 64(%rdx)
|
||||
; SSE-NEXT: movaps %xmm10, 32(%rdx)
|
||||
; SSE-NEXT: movaps %xmm11, (%rdx)
|
||||
; SSE-NEXT: movaps %xmm12, 112(%rdx)
|
||||
; SSE-NEXT: movaps %xmm15, 80(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 48(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 16(%rdx)
|
||||
; SSE-NEXT: movaps %xmm0, 96(%rcx)
|
||||
; SSE-NEXT: movaps %xmm1, 112(%rcx)
|
||||
; SSE-NEXT: movaps %xmm7, 64(%rcx)
|
||||
; SSE-NEXT: movaps %xmm4, 80(%rcx)
|
||||
; SSE-NEXT: movaps %xmm14, 32(%rcx)
|
||||
; SSE-NEXT: movaps %xmm13, 48(%rcx)
|
||||
; SSE-NEXT: movaps %xmm9, (%rcx)
|
||||
; SSE-NEXT: movaps %xmm5, 16(%rcx)
|
||||
; SSE-NEXT: addq $360, %rsp # imm = 0x168
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: load_i32_stride3_vf32:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: subq $392, %rsp # imm = 0x188
|
||||
; AVX1-NEXT: vmovaps 320(%rdi), %ymm3
|
||||
; AVX1-NEXT: vmovups %ymm3, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 288(%rdi), %ymm4
|
||||
; AVX1-NEXT: vmovups %ymm4, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps (%rdi), %ymm2
|
||||
; AVX1-NEXT: vmovups %ymm2, (%rsp) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %ymm6
|
||||
; AVX1-NEXT: vmovups %ymm6, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 128(%rdi), %ymm1
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %ymm5
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm5[0],ymm1[1],ymm5[2,3],ymm1[4],ymm5[5,6],ymm1[7]
|
||||
; AVX1-NEXT: vmovaps %ymm5, %ymm9
|
||||
; AVX1-NEXT: vmovaps %ymm1, %ymm10
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,3,2,1]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,3,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovaps 176(%rdi), %xmm5
|
||||
; AVX1-NEXT: vmovaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 160(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm1 = zero,zero,xmm1[2],xmm5[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 80(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = zero,zero,xmm0[2],xmm1[1]
|
||||
; AVX1-NEXT: vmovaps %xmm1, %xmm8
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0],ymm6[1],ymm2[2,3],ymm6[4],ymm2[5,6],ymm6[7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm1 = xmm1[0,1],xmm2[2],xmm1[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,3,2,1]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[0,3,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm4[0],ymm3[1],ymm4[2,3],ymm3[4],ymm4[5,6],ymm3[7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,3,2,1]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,3,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovaps 368(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 352(%rdi), %xmm11
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm1 = zero,zero,xmm11[2],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 224(%rdi), %ymm1
|
||||
; AVX1-NEXT: vmovaps 192(%rdi), %ymm2
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0],ymm1[1],ymm2[2,3],ymm1[4],ymm2[5,6],ymm1[7]
|
||||
; AVX1-NEXT: vmovaps %ymm2, %ymm3
|
||||
; AVX1-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps %ymm1, %ymm2
|
||||
; AVX1-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,3,2,1]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,3,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm12
|
||||
; AVX1-NEXT: vmovaps 272(%rdi), %xmm15
|
||||
; AVX1-NEXT: vmovaps 256(%rdi), %xmm14
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm13 = zero,zero,xmm14[2],xmm15[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm13, %ymm0, %ymm13
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm12[0,1,2,3,4,5],ymm13[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm12 = ymm3[0,1],ymm2[2],ymm3[3,4],ymm2[5],ymm3[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm12, %xmm13
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm7 = xmm13[0],xmm12[1,2],xmm13[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[1,0,3,2]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm13[1,1,3,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm7, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm7 = xmm14[0,1],xmm15[2],xmm14[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[0,0,3,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps %ymm10, %ymm12
|
||||
; AVX1-NEXT: vmovaps %ymm9, %ymm5
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm9[0,1],ymm10[2],ymm9[3,4],ymm10[5],ymm9[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm7[0],xmm6[1,2],xmm7[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[1,0,3,2]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm10 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm9 # 16-byte Reload
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm7 = xmm9[0,1],xmm10[2],xmm9[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[0,0,3,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovups (%rsp), %ymm3 # 32-byte Reload
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm3[0,1],ymm4[2],ymm3[3,4],ymm4[5],ymm3[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm7[0],xmm6[1,2],xmm7[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[1,0,3,2]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm8, %xmm0
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm7 = xmm1[0,1],xmm8[2],xmm1[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[0,0,3,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm6[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm13 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm13[0,1],ymm2[2],ymm13[3,4],ymm2[5],ymm13[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm7[0],xmm6[1,2],xmm7[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[1,0,3,2]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Reload
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm7 = xmm11[0,1],xmm8[2],xmm11[3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[0,0,3,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm6[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm6, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm12[0,1],ymm5[2],ymm12[3,4],ymm5[5],ymm12[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0],xmm7[1],xmm6[2,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[2,1,0,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[2,3,0,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm9[0,1],xmm10[0,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm12 = ymm6[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm1[0,1],xmm0[0,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm4[0,1],ymm3[2],ymm4[3,4],ymm3[5],ymm4[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0],xmm7[1],xmm6[2,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[2,1,0,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[2,3,0,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm0, %ymm5
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm5 = ymm6[0,1,2,3,4],ymm5[5,6,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm2[0,1],ymm13[2],ymm2[3,4],ymm13[5],ymm2[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0],xmm7[1],xmm6[2,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[2,1,0,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[2,3,0,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm11[0,1],xmm8[0,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm3
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm6[0,1,2,3,4],ymm3[5,6,7]
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vblendps $36, {{[-0-9]+}}(%r{{[sb]}}p), %ymm0, %ymm2 # 32-byte Folded Reload
|
||||
; AVX1-NEXT: # ymm2 = ymm0[0,1],mem[2],ymm0[3,4],mem[5],ymm0[6,7]
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm2 = xmm2[0],xmm4[1],xmm2[2,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[2,1,0,3]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[2,3,0,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm14[0,1],xmm15[0,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3,4],ymm0[5,6,7]
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 64(%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 96(%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, (%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 32(%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 96(%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, (%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 32(%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 64(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm0, 64(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm3, 96(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm5, (%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm12, 32(%rcx)
|
||||
; AVX1-NEXT: addq $392, %rsp # imm = 0x188
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: load_i32_stride3_vf32:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: subq $136, %rsp
|
||||
; AVX2-SLOW-NEXT: vmovaps 320(%rdi), %ymm15
|
||||
; AVX2-SLOW-NEXT: vmovaps 224(%rdi), %ymm3
|
||||
; AVX2-SLOW-NEXT: vmovaps 192(%rdi), %ymm2
|
||||
; AVX2-SLOW-NEXT: vmovaps 256(%rdi), %ymm1
|
||||
; AVX2-SLOW-NEXT: vmovaps 128(%rdi), %ymm6
|
||||
; AVX2-SLOW-NEXT: vmovaps 160(%rdi), %ymm10
|
||||
; AVX2-SLOW-NEXT: vmovaps (%rdi), %ymm4
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm4, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vmovaps 32(%rdi), %ymm7
|
||||
; AVX2-SLOW-NEXT: vmovaps 64(%rdi), %ymm0
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vmovaps 96(%rdi), %ymm14
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd {{.*#+}} ymm12 = [21474836482,21474836482,21474836482,21474836482]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm0, %ymm12, %ymm0
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm5 = ymm4[0],ymm7[1],ymm4[2,3],ymm7[4],ymm4[5,6],ymm7[7]
|
||||
; AVX2-SLOW-NEXT: vmovaps {{.*#+}} ymm13 = <0,3,6,1,4,7,u,u>
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm5, %ymm13, %ymm5
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm5[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm10, %ymm12, %ymm0
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm5 = ymm14[0],ymm6[1],ymm14[2,3],ymm6[4],ymm14[5,6],ymm6[7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm5, %ymm13, %ymm5
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm5[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm1, %ymm12, %ymm0
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm3, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm9 = ymm2[0],ymm3[1],ymm2[2,3],ymm3[4],ymm2[5,6],ymm3[7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm9, %ymm13, %ymm9
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm9[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vmovaps 288(%rdi), %ymm11
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm15, %ymm4
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm15 = ymm11[0],ymm15[1],ymm11[2,3],ymm15[4],ymm11[5,6],ymm15[7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm15, %ymm13, %ymm13
|
||||
; AVX2-SLOW-NEXT: vmovaps 352(%rdi), %ymm8
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm8, %ymm12, %ymm12
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm13[0,1,2,3,4,5],ymm12[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, (%rsp) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm12 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovaps {{.*#+}} ymm3 = <1,4,7,2,5,u,u,u>
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm12, %ymm3, %ymm12
|
||||
; AVX2-SLOW-NEXT: vbroadcastf128 {{.*#+}} ymm0 = [0,0,3,6,0,0,3,6]
|
||||
; AVX2-SLOW-NEXT: # ymm0 = mem[0,1,0,1]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm1, %ymm0, %ymm15
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm1, %ymm13
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm12 = ymm12[0,1,2,3,4],ymm15[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm15 = ymm14[0,1],ymm6[2],ymm14[3,4],ymm6[5],ymm14[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm15, %ymm3, %ymm15
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm10, %ymm0, %ymm5
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm15 = ymm15[0,1,2,3,4],ymm5[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm5 = ymm1[0,1],ymm7[2],ymm1[3,4],ymm7[5],ymm1[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm5, %ymm3, %ymm5
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm2, %ymm0, %ymm9
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1,2,3,4],ymm9[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm9 = ymm11[0,1],ymm4[2],ymm11[3,4],ymm4[5],ymm11[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm9, %ymm3, %ymm3
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm8, %ymm0, %ymm0
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1,2,3,4],ymm0[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm3 = ymm6[0,1],ymm14[2],ymm6[3,4],ymm14[5],ymm6[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovaps {{.*#+}} ymm9 = <2,5,0,3,6,u,u,u>
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm3, %ymm9, %ymm3
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm10 = ymm10[0,1,0,3,4,5,4,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm10 = ymm10[0,1,0,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1,2,3,4],ymm10[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm6 = ymm7[0,1],ymm1[2],ymm7[3,4],ymm1[5],ymm7[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm6, %ymm9, %ymm6
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm7 = ymm2[0,1,0,3,4,5,4,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm7 = ymm7[0,1,0,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm6 = ymm6[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm2 = ymm4[0,1],ymm11[2],ymm4[3,4],ymm11[5],ymm4[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm2, %ymm9, %ymm2
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm1 = ymm8[0,1,0,3,4,5,4,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1,2,3,4],ymm1[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vblendps $36, {{[-0-9]+}}(%r{{[sb]}}p), %ymm2, %ymm2 # 32-byte Folded Reload
|
||||
; AVX2-SLOW-NEXT: # ymm2 = ymm2[0,1],mem[2],ymm2[3,4],mem[5],ymm2[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermps %ymm2, %ymm9, %ymm2
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm4 = ymm13[0,1,0,3,4,5,4,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[0,1,0,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1,2,3,4],ymm4[5,6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups (%rsp), %ymm4 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm4, 96(%rsi)
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm4, 64(%rsi)
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm4, 32(%rsi)
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm4, (%rsi)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm0, 96(%rdx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm5, (%rdx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm15, 32(%rdx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm12, 64(%rdx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm2, 64(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm1, 96(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm6, (%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm3, 32(%rcx)
|
||||
; AVX2-SLOW-NEXT: addq $136, %rsp
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-ALL-LABEL: load_i32_stride3_vf32:
|
||||
; AVX2-FAST-ALL: # %bb.0:
|
||||
; AVX2-FAST-ALL-NEXT: subq $72, %rsp
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 320(%rdi), %ymm1
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 224(%rdi), %ymm0
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 192(%rdi), %ymm2
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 256(%rdi), %ymm3
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 128(%rdi), %ymm9
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 160(%rdi), %ymm10
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps (%rdi), %ymm5
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 32(%rdi), %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 64(%rdi), %ymm8
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 96(%rdi), %ymm12
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd {{.*#+}} ymm4 = [21474836482,21474836482,21474836482,21474836482]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm8, %ymm4, %ymm6
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm11 = ymm5[0],ymm7[1],ymm5[2,3],ymm7[4],ymm5[5,6],ymm7[7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm13 = <0,3,6,1,4,7,u,u>
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm11, %ymm13, %ymm11
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm6 = ymm11[0,1,2,3,4,5],ymm6[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm6, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm10, %ymm4, %ymm6
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm11 = ymm12[0],ymm9[1],ymm12[2,3],ymm9[4],ymm12[5,6],ymm9[7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm11, %ymm13, %ymm11
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm6 = ymm11[0,1,2,3,4,5],ymm6[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm6, (%rsp) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm3, %ymm6
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm3, %ymm4, %ymm11
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm14 = ymm2[0],ymm0[1],ymm2[2,3],ymm0[4],ymm2[5,6],ymm0[7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm14, %ymm13, %ymm14
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm3 = ymm14[0,1,2,3,4,5],ymm11[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm3, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 288(%rdi), %ymm15
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm14 = ymm15[0],ymm1[1],ymm15[2,3],ymm1[4],ymm15[5,6],ymm1[7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm1, %ymm3
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm14, %ymm13, %ymm13
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 352(%rdi), %ymm1
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm4, %ymm4
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm4 = ymm13[0,1,2,3,4,5],ymm4[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm4, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm4 = ymm2[0,1],ymm0[2],ymm2[3,4],ymm0[5],ymm2[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm2 = <1,4,7,2,5,u,u,u>
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm4, %ymm2, %ymm4
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastf128 {{.*#+}} ymm0 = [0,0,3,6,0,0,3,6]
|
||||
; AVX2-FAST-ALL-NEXT: # ymm0 = mem[0,1,0,1]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm6, %ymm0, %ymm13
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm6, %ymm14
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm13 = ymm4[0,1,2,3,4],ymm13[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm4 = ymm12[0,1],ymm9[2],ymm12[3,4],ymm9[5],ymm12[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm4, %ymm2, %ymm4
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm10, %ymm0, %ymm6
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm4 = ymm4[0,1,2,3,4],ymm6[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm6 = ymm5[0,1],ymm7[2],ymm5[3,4],ymm7[5],ymm5[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm6, %ymm2, %ymm6
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm8, %ymm0, %ymm11
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm6 = ymm6[0,1,2,3,4],ymm11[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm11 = ymm15[0,1],ymm3[2],ymm15[3,4],ymm3[5],ymm15[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm11, %ymm2, %ymm2
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm0, %ymm0
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3,4],ymm0[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm9[0,1],ymm12[2],ymm9[3,4],ymm12[5],ymm9[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm9 = [0,1,0,3,0,1,4,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm10, %ymm9, %ymm10
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm11 = <2,5,0,3,6,u,u,u>
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm2, %ymm11, %ymm2
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1,2,3,4],ymm10[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm5 = ymm7[0,1],ymm5[2],ymm7[3,4],ymm5[5],ymm7[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm8, %ymm9, %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm5, %ymm11, %ymm5
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm7 = ymm3[0,1],ymm15[2],ymm3[3,4],ymm15[5],ymm3[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm9, %ymm1
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm7, %ymm11, %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm1 = ymm7[0,1,2,3,4],ymm1[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm14, %ymm9, %ymm3
|
||||
; AVX2-FAST-ALL-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm7 # 32-byte Reload
|
||||
; AVX2-FAST-ALL-NEXT: vblendps $36, {{[-0-9]+}}(%r{{[sb]}}p), %ymm7, %ymm7 # 32-byte Folded Reload
|
||||
; AVX2-FAST-ALL-NEXT: # ymm7 = ymm7[0,1],mem[2],ymm7[3,4],mem[5],ymm7[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm7, %ymm11, %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm3 = ymm7[0,1,2,3,4],ymm3[5,6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm7 # 32-byte Reload
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm7, 96(%rsi)
|
||||
; AVX2-FAST-ALL-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm7 # 32-byte Reload
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm7, 64(%rsi)
|
||||
; AVX2-FAST-ALL-NEXT: vmovups (%rsp), %ymm7 # 32-byte Reload
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm7, 32(%rsi)
|
||||
; AVX2-FAST-ALL-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm7 # 32-byte Reload
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm7, (%rsi)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm0, 96(%rdx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm6, (%rdx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm4, 32(%rdx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm13, 64(%rdx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm3, 64(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm1, 96(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm5, (%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm2, 32(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: addq $72, %rsp
|
||||
; AVX2-FAST-ALL-NEXT: vzeroupper
|
||||
; AVX2-FAST-ALL-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-PERLANE-LABEL: load_i32_stride3_vf32:
|
||||
; AVX2-FAST-PERLANE: # %bb.0:
|
||||
; AVX2-FAST-PERLANE-NEXT: subq $136, %rsp
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 320(%rdi), %ymm15
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 224(%rdi), %ymm3
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 192(%rdi), %ymm2
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 256(%rdi), %ymm1
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 128(%rdi), %ymm6
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 160(%rdi), %ymm10
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps (%rdi), %ymm4
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm4, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 32(%rdi), %ymm7
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 64(%rdi), %ymm0
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 96(%rdi), %ymm14
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd {{.*#+}} ymm12 = [21474836482,21474836482,21474836482,21474836482]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm0, %ymm12, %ymm0
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm5 = ymm4[0],ymm7[1],ymm4[2,3],ymm7[4],ymm4[5,6],ymm7[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps {{.*#+}} ymm13 = <0,3,6,1,4,7,u,u>
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm5, %ymm13, %ymm5
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm5[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm10, %ymm12, %ymm0
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm5 = ymm14[0],ymm6[1],ymm14[2,3],ymm6[4],ymm14[5,6],ymm6[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm5, %ymm13, %ymm5
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm5[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm1, %ymm12, %ymm0
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm3, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm9 = ymm2[0],ymm3[1],ymm2[2,3],ymm3[4],ymm2[5,6],ymm3[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm9, %ymm13, %ymm9
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm9[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 288(%rdi), %ymm11
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm15, %ymm4
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm15 = ymm11[0],ymm15[1],ymm11[2,3],ymm15[4],ymm11[5,6],ymm15[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm15, %ymm13, %ymm13
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 352(%rdi), %ymm8
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm8, %ymm12, %ymm12
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm13[0,1,2,3,4,5],ymm12[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, (%rsp) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm12 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps {{.*#+}} ymm3 = <1,4,7,2,5,u,u,u>
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm12, %ymm3, %ymm12
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastf128 {{.*#+}} ymm0 = [0,0,3,6,0,0,3,6]
|
||||
; AVX2-FAST-PERLANE-NEXT: # ymm0 = mem[0,1,0,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm1, %ymm0, %ymm15
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm1, %ymm13
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm12 = ymm12[0,1,2,3,4],ymm15[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm15 = ymm14[0,1],ymm6[2],ymm14[3,4],ymm6[5],ymm14[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm15, %ymm3, %ymm15
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm10, %ymm0, %ymm5
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm15 = ymm15[0,1,2,3,4],ymm5[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm5 = ymm1[0,1],ymm7[2],ymm1[3,4],ymm7[5],ymm1[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm5, %ymm3, %ymm5
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm2, %ymm0, %ymm9
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1,2,3,4],ymm9[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm9 = ymm11[0,1],ymm4[2],ymm11[3,4],ymm4[5],ymm11[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm9, %ymm3, %ymm3
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm8, %ymm0, %ymm0
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1,2,3,4],ymm0[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm3 = ymm6[0,1],ymm14[2],ymm6[3,4],ymm14[5],ymm6[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps {{.*#+}} ymm9 = <2,5,0,3,6,u,u,u>
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm3, %ymm9, %ymm3
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm10 = ymm10[0,1,0,3,4,5,4,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm10 = ymm10[0,1,0,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1,2,3,4],ymm10[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm6 = ymm7[0,1],ymm1[2],ymm7[3,4],ymm1[5],ymm7[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm6, %ymm9, %ymm6
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm7 = ymm2[0,1,0,3,4,5,4,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm7 = ymm7[0,1,0,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm6 = ymm6[0,1,2,3,4],ymm7[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm2 = ymm4[0,1],ymm11[2],ymm4[3,4],ymm11[5],ymm4[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm2, %ymm9, %ymm2
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm1 = ymm8[0,1,0,3,4,5,4,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1,2,3,4],ymm1[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps $36, {{[-0-9]+}}(%r{{[sb]}}p), %ymm2, %ymm2 # 32-byte Folded Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: # ymm2 = ymm2[0,1],mem[2],ymm2[3,4],mem[5],ymm2[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermps %ymm2, %ymm9, %ymm2
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm4 = ymm13[0,1,0,3,4,5,4,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[0,1,0,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1,2,3,4],ymm4[5,6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups (%rsp), %ymm4 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm4, 96(%rsi)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm4, 64(%rsi)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm4, 32(%rsi)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm4, (%rsi)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm0, 96(%rdx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm5, (%rdx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm15, 32(%rdx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm12, 64(%rdx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm2, 64(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm1, 96(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm6, (%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm3, 32(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: addq $136, %rsp
|
||||
; AVX2-FAST-PERLANE-NEXT: vzeroupper
|
||||
; AVX2-FAST-PERLANE-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: load_i32_stride3_vf32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 320(%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 256(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 128(%rdi), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 192(%rdi), %zmm5
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm6 = <0,3,6,9,12,15,18,21,24,27,30,u,u,u,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm7
|
||||
; AVX512-NEXT: vpermt2d %zmm1, %zmm6, %zmm7
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm8 = [0,1,2,3,4,5,6,7,8,9,10,17,20,23,26,29]
|
||||
; AVX512-NEXT: vpermt2d %zmm0, %zmm8, %zmm7
|
||||
; AVX512-NEXT: vpermi2d %zmm3, %zmm2, %zmm6
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm8, %zmm6
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm8 = <17,20,23,26,29,0,3,6,9,12,15,u,u,u,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm1, %zmm9
|
||||
; AVX512-NEXT: vpermt2d %zmm5, %zmm8, %zmm9
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm10 = [0,1,2,3,4,5,6,7,8,9,10,18,21,24,27,30]
|
||||
; AVX512-NEXT: vpermt2d %zmm0, %zmm10, %zmm9
|
||||
; AVX512-NEXT: vpermi2d %zmm2, %zmm3, %zmm8
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm10, %zmm8
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm10 = <2,5,8,11,14,17,20,23,26,29,u,u,u,u,u,u>
|
||||
; AVX512-NEXT: vpermt2d %zmm1, %zmm10, %zmm5
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm1 = [0,1,2,3,4,5,6,7,8,9,16,19,22,25,28,31]
|
||||
; AVX512-NEXT: vpermt2d %zmm0, %zmm1, %zmm5
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm10, %zmm2
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm1, %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 %zmm7, 64(%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm6, (%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm9, 64(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm8, (%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm5, 64(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm2, (%rcx)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%wide.vec = load <96 x i32>, <96 x i32>* %in.vec, align 32
|
||||
|
||||
%strided.vec0 = shufflevector <96 x i32> %wide.vec, <96 x i32> poison, <32 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45, i32 48, i32 51, i32 54, i32 57, i32 60, i32 63, i32 66, i32 69, i32 72, i32 75, i32 78, i32 81, i32 84, i32 87, i32 90, i32 93>
|
||||
%strided.vec1 = shufflevector <96 x i32> %wide.vec, <96 x i32> poison, <32 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46, i32 49, i32 52, i32 55, i32 58, i32 61, i32 64, i32 67, i32 70, i32 73, i32 76, i32 79, i32 82, i32 85, i32 88, i32 91, i32 94>
|
||||
%strided.vec2 = shufflevector <96 x i32> %wide.vec, <96 x i32> poison, <32 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47, i32 50, i32 53, i32 56, i32 59, i32 62, i32 65, i32 68, i32 71, i32 74, i32 77, i32 80, i32 83, i32 86, i32 89, i32 92, i32 95>
|
||||
|
||||
store <32 x i32> %strided.vec0, <32 x i32>* %out.vec0, align 32
|
||||
store <32 x i32> %strided.vec1, <32 x i32>* %out.vec1, align 32
|
||||
store <32 x i32> %strided.vec2, <32 x i32>* %out.vec2, align 32
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
|
|
@ -796,3 +796,908 @@ define void @load_i32_stride4_vf16(<64 x i32>* %in.vec, <16 x i32>* %out.vec0, <
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @load_i32_stride4_vf32(<128 x i32>* %in.vec, <32 x i32>* %out.vec0, <32 x i32>* %out.vec1, <32 x i32>* %out.vec2, <32 x i32>* %out.vec3) nounwind {
|
||||
; SSE-LABEL: load_i32_stride4_vf32:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $456, %rsp # imm = 0x1C8
|
||||
; SSE-NEXT: movaps 336(%rdi), %xmm8
|
||||
; SSE-NEXT: movaps %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 368(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 352(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 208(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 192(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 240(%rdi), %xmm6
|
||||
; SSE-NEXT: movaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 224(%rdi), %xmm14
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm4
|
||||
; SSE-NEXT: movaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm11
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm11 = xmm11[0],xmm0[0],xmm11[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm11[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm14, %xmm1
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1]
|
||||
; SSE-NEXT: movaps %xmm5, %xmm3
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm3 = xmm3[0],xmm7[0],xmm3[1],xmm7[1]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm11[1]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm3, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm10, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm9[0],xmm0[1],xmm9[1]
|
||||
; SSE-NEXT: movaps %xmm9, %xmm7
|
||||
; SSE-NEXT: movaps 320(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm8[0],xmm1[1],xmm8[1]
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 496(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 480(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 464(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 448(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 176(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 160(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps %xmm9, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 144(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 128(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 304(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 288(%rdi), %xmm13
|
||||
; SSE-NEXT: movaps %xmm13, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 272(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 256(%rdi), %xmm15
|
||||
; SSE-NEXT: movaps %xmm15, %xmm12
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm12 = xmm12[0],xmm1[0],xmm12[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 432(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 416(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps %xmm10, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 400(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 384(%rdi), %xmm8
|
||||
; SSE-NEXT: movaps %xmm8, %xmm3
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm3, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm2, %xmm1
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
|
||||
; SSE-NEXT: movaps (%rdi), %xmm5
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm5, %xmm4
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm4, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm1[1]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm6 = xmm6[2],mem[2],xmm6[3],mem[3]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm0 = xmm0[2],mem[2],xmm0[3],mem[3]
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm14 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm14 = xmm14[2],mem[2],xmm14[3],mem[3]
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm14 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm14 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm14 = xmm14[2],mem[2],xmm14[3],mem[3]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm11 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm11 = xmm11[2],xmm7[2],xmm11[3],xmm7[3]
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm7 = xmm7[2],mem[2],xmm7[3],mem[3]
|
||||
; SSE-NEXT: movaps %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm11 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm11 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm11 = xmm11[2],mem[2],xmm11[3],mem[3]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm7 = xmm7[2],mem[2],xmm7[3],mem[3]
|
||||
; SSE-NEXT: movaps %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm9 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm9 = xmm9[2],mem[2],xmm9[3],mem[3]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Reload
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm7 = xmm7[2],mem[2],xmm7[3],mem[3]
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm13 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm13 = xmm13[2],mem[2],xmm13[3],mem[3]
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm15 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm15 = xmm15[2],mem[2],xmm15[3],mem[3]
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm10 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm10 = xmm10[2],mem[2],xmm10[3],mem[3]
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm8 = xmm8[2],mem[2],xmm8[3],mem[3]
|
||||
; SSE-NEXT: unpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm2 = xmm2[2],mem[2],xmm2[3],mem[3]
|
||||
; SSE-NEXT: unpckhps (%rsp), %xmm5 # 16-byte Folded Reload
|
||||
; SSE-NEXT: # xmm5 = xmm5[2],mem[2],xmm5[3],mem[3]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm6[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm6[1]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm14, %xmm0
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, %xmm1
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm14 # 16-byte Reload
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm14[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm14[1]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm6, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm11[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm6 = xmm6[1],xmm11[1]
|
||||
; SSE-NEXT: movaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm7, %xmm14
|
||||
; SSE-NEXT: movaps %xmm7, %xmm11
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm11 = xmm11[0],xmm9[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm9[1]
|
||||
; SSE-NEXT: movaps %xmm15, %xmm9
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm9 = xmm9[0],xmm13[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm15 = xmm15[1],xmm13[1]
|
||||
; SSE-NEXT: movaps %xmm8, %xmm7
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm7 = xmm7[0],xmm10[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm8 = xmm8[1],xmm10[1]
|
||||
; SSE-NEXT: movaps %xmm5, %xmm6
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm6 = xmm6[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm2[1]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 96(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 64(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 32(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, (%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 112(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 80(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 48(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 16(%rsi)
|
||||
; SSE-NEXT: movaps %xmm3, 96(%rdx)
|
||||
; SSE-NEXT: movaps %xmm12, 64(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 32(%rdx)
|
||||
; SSE-NEXT: movaps %xmm4, (%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 112(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 80(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 48(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm2, 16(%rdx)
|
||||
; SSE-NEXT: movaps %xmm7, 96(%rcx)
|
||||
; SSE-NEXT: movaps %xmm9, 64(%rcx)
|
||||
; SSE-NEXT: movaps %xmm11, 32(%rcx)
|
||||
; SSE-NEXT: movaps %xmm6, (%rcx)
|
||||
; SSE-NEXT: movaps %xmm0, 112(%rcx)
|
||||
; SSE-NEXT: movaps %xmm1, 80(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%rcx)
|
||||
; SSE-NEXT: movaps %xmm8, 96(%r8)
|
||||
; SSE-NEXT: movaps %xmm15, 64(%r8)
|
||||
; SSE-NEXT: movaps %xmm14, 32(%r8)
|
||||
; SSE-NEXT: movaps %xmm5, (%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%r8)
|
||||
; SSE-NEXT: addq $456, %rsp # imm = 0x1C8
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: load_i32_stride4_vf32:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: subq $744, %rsp # imm = 0x2E8
|
||||
; AVX1-NEXT: vmovaps 416(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 432(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vmovaps 400(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 384(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,0]
|
||||
; AVX1-NEXT: vmovaps 464(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 448(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
|
||||
; AVX1-NEXT: vmovaps 480(%rdi), %xmm3
|
||||
; AVX1-NEXT: vmovaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 496(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[0,0],xmm3[0,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[0,1,2,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm2
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1,2,3,4,5],ymm2[6,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 288(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 304(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
||||
; AVX1-NEXT: vmovaps 272(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 256(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,0]
|
||||
; AVX1-NEXT: vmovaps 336(%rdi), %xmm14
|
||||
; AVX1-NEXT: vmovaps 320(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1]
|
||||
; AVX1-NEXT: vmovaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
|
||||
; AVX1-NEXT: vmovaps 352(%rdi), %xmm11
|
||||
; AVX1-NEXT: vmovaps 368(%rdi), %xmm12
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm12[0,0],xmm11[0,0]
|
||||
; AVX1-NEXT: vmovaps %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[0,1,2,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm2
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1,2,3,4,5],ymm2[6,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 160(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 176(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
||||
; AVX1-NEXT: vmovaps 144(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 128(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm8 = xmm1[0,1],xmm0[2,0]
|
||||
; AVX1-NEXT: vmovaps 208(%rdi), %xmm5
|
||||
; AVX1-NEXT: vmovaps 192(%rdi), %xmm10
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm10[0],xmm5[0],xmm10[1],xmm5[1]
|
||||
; AVX1-NEXT: vmovaps %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm9
|
||||
; AVX1-NEXT: vmovaps 224(%rdi), %xmm3
|
||||
; AVX1-NEXT: vmovaps 240(%rdi), %xmm4
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm4[0,0],xmm3[0,0]
|
||||
; AVX1-NEXT: vmovaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[0,1,2,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm7 = ymm9[0,1,2,3,4,5],ymm7[6,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm8[0,1,2,3],ymm7[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 80(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm7 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %xmm13
|
||||
; AVX1-NEXT: vmovaps 112(%rdi), %xmm15
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm6 = xmm15[0,0],xmm13[0,0]
|
||||
; AVX1-NEXT: vmovaps %xmm15, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[0,1,2,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm7 = ymm7[0,1,2,3,4,5],ymm6[6,7]
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 48(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vmovaps (%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 16(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm6 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm6[0,1],xmm0[2,0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm7[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm11[0],xmm12[0],xmm11[1],xmm12[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vinsertps $12, {{[-0-9]+}}(%r{{[sb]}}p), %xmm14, %xmm6 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm6 = mem[0],xmm14[1],zero,zero
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm11 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps $12, {{[-0-9]+}}(%r{{[sb]}}p), %xmm11, %xmm6 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm6 = mem[0],xmm11[1],zero,zero
|
||||
; AVX1-NEXT: vmovaps (%rsp), %xmm14 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpcklps {{[-0-9]+}}(%r{{[sb]}}p), %xmm14, %xmm7 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm7 = xmm14[0],mem[0],xmm14[1],mem[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0,1],xmm7[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm6 = xmm10[1],xmm5[1],zero,zero
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps $12, {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm6 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm6 = mem[0],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpcklps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm7 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm7 = xmm1[0],mem[0],xmm1[1],mem[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0,1],xmm7[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm10 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm3[0],xmm10[0],xmm3[1],xmm10[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm12 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm6 = xmm12[1],xmm2[1],zero,zero
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm9 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm5 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm6 = xmm9[1],xmm5[1],zero,zero
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm7 = xmm1[0],xmm8[0],xmm1[1],xmm8[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0,1],xmm7[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm13[0],xmm15[0],xmm13[1],xmm15[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm13 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm6 = xmm13[1],xmm4[1],zero,zero
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm15 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpcklps {{[-0-9]+}}(%r{{[sb]}}p), %xmm15, %xmm6 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm6 = xmm15[0],mem[0],xmm15[1],mem[1]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps $12, {{[-0-9]+}}(%r{{[sb]}}p), %xmm7, %xmm7 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm7 = mem[0],xmm7[1],zero,zero
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm7[0,1],xmm6[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm0 = zero,zero,xmm0[2],mem[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6, %xmm6 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm6 = xmm6[2],mem[2],xmm6[3],mem[3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm6 = xmm6[2],xmm11[2],xmm6[3],xmm11[3]
|
||||
; AVX1-NEXT: vinsertps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm14, %xmm7 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm7 = zero,zero,xmm14[2],mem[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0,1],xmm7[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm0 = zero,zero,xmm0[2],mem[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6, %xmm6 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm6 = xmm6[2],mem[2],xmm6[3],mem[3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm14 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm14, %xmm6 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm6 = xmm14[2],mem[2],xmm14[3],mem[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm11 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm11, %xmm7 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm7 = zero,zero,xmm11[2],mem[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0,1],xmm7[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = zero,zero,xmm3[2],xmm10[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm6 = xmm12[2],xmm2[2],xmm12[3],xmm2[3]
|
||||
; AVX1-NEXT: vmovaps %xmm12, %xmm3
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm6 = xmm9[2],xmm5[2],xmm9[3],xmm5[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm7 = zero,zero,xmm1[2],xmm8[2]
|
||||
; AVX1-NEXT: vmovaps %xmm1, %xmm12
|
||||
; AVX1-NEXT: vmovaps %xmm8, %xmm10
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0,1],xmm7[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm8 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm5 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = zero,zero,xmm8[2],xmm5[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm6 = xmm13[2],xmm4[2],xmm13[3],xmm4[3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm13 # 16-byte Reload
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm6 = zero,zero,xmm15[2],xmm13[2]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm15 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm9 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm7 = xmm9[2],xmm15[2],xmm9[3],xmm15[3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm6 = xmm7[0,1],xmm6[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm0 = xmm0[2],mem[2],xmm0[3],mem[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vshufps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm1 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm1 = xmm1[3,0],mem[3,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm11, %xmm1 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm1 = xmm11[2],mem[2],xmm11[3],mem[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[3,0],xmm14[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[2,0,2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm1 = xmm2[0,1],xmm1[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm1 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm1 = xmm1[2],mem[2],xmm1[3],mem[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[3,0],xmm3[3,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm1
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm2
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1,2,3,4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm2 = xmm12[2],xmm10[2],xmm12[3],xmm10[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vshufps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm3, %xmm3 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm3 = xmm3[3,0],mem[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[2,0,2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm2 = xmm3[0,1],xmm2[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1,2,3],ymm1[4,5,6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2, %xmm2 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm2 = xmm2[2],mem[2],xmm2[3],mem[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vshufps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm3, %xmm3 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm3 = xmm3[3,0],mem[3,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm2
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm3
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0,1,2,3,4,5],ymm2[6,7]
|
||||
; AVX1-NEXT: vmovaps (%rsp), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3, %xmm3 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm3 = xmm3[2],mem[2],xmm3[3],mem[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vshufps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm4, %xmm4 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm4 = xmm4[3,0],mem[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[2,0,2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm3 = xmm4[0,1],xmm3[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm3 = xmm8[2],xmm5[2],xmm8[3],xmm5[3]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vshufps $51, {{[-0-9]+}}(%r{{[sb]}}p), %xmm4, %xmm4 # 16-byte Folded Reload
|
||||
; AVX1-NEXT: # xmm4 = xmm4[3,0],mem[3,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm3
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm4
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3,4,5],ymm3[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm4 = xmm4[2],xmm13[2],xmm4[3],xmm13[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm15[3,0],xmm9[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm5 = xmm5[2,0,2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} xmm4 = xmm5[0,1],xmm4[2,3]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3],ymm3[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, (%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 32(%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 64(%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 96(%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 96(%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, (%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 32(%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 64(%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 96(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm6, (%rcx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 32(%rcx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm4, 64(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm2, 64(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm1, 96(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm3, (%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm0, 32(%r8)
|
||||
; AVX1-NEXT: addq $744, %rsp # imm = 0x2E8
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: load_i32_stride4_vf32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: subq $696, %rsp # imm = 0x2B8
|
||||
; AVX2-NEXT: vmovaps 288(%rdi), %ymm12
|
||||
; AVX2-NEXT: vmovaps 320(%rdi), %ymm5
|
||||
; AVX2-NEXT: vmovaps 352(%rdi), %ymm6
|
||||
; AVX2-NEXT: vmovaps 416(%rdi), %ymm7
|
||||
; AVX2-NEXT: vmovups %ymm7, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 448(%rdi), %ymm2
|
||||
; AVX2-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 480(%rdi), %ymm1
|
||||
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm3 = [17179869184,17179869184,17179869184,17179869184]
|
||||
; AVX2-NEXT: vpermps %ymm1, %ymm3, %ymm0
|
||||
; AVX2-NEXT: vmovaps %ymm1, %ymm14
|
||||
; AVX2-NEXT: vpermps %ymm2, %ymm3, %ymm1
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vmovaps 400(%rdi), %xmm2
|
||||
; AVX2-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 384(%rdi), %xmm1
|
||||
; AVX2-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
||||
; AVX2-NEXT: vmovaps {{.*#+}} xmm4 = <u,u,0,4>
|
||||
; AVX2-NEXT: vpermps %ymm7, %ymm4, %ymm2
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm6, %ymm3, %ymm0
|
||||
; AVX2-NEXT: vpermps %ymm5, %ymm3, %ymm1
|
||||
; AVX2-NEXT: vmovaps %ymm5, %ymm9
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vmovaps 272(%rdi), %xmm2
|
||||
; AVX2-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 256(%rdi), %xmm1
|
||||
; AVX2-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
||||
; AVX2-NEXT: vpermps %ymm12, %ymm4, %ymm2
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3]
|
||||
; AVX2-NEXT: vmovaps 192(%rdi), %ymm5
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 224(%rdi), %ymm10
|
||||
; AVX2-NEXT: vpermps %ymm10, %ymm3, %ymm0
|
||||
; AVX2-NEXT: vpermps %ymm5, %ymm3, %ymm2
|
||||
; AVX2-NEXT: vmovaps %ymm5, %ymm8
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vmovaps 160(%rdi), %ymm1
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 144(%rdi), %xmm5
|
||||
; AVX2-NEXT: vmovaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 128(%rdi), %xmm2
|
||||
; AVX2-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1]
|
||||
; AVX2-NEXT: vpermps %ymm1, %ymm4, %ymm5
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm2 = xmm2[0,1],xmm5[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %ymm15
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %ymm11
|
||||
; AVX2-NEXT: vpermps %ymm11, %ymm3, %ymm5
|
||||
; AVX2-NEXT: vpermps %ymm15, %ymm3, %ymm3
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1,2,3,4,5],ymm5[6,7]
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %ymm0
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm0, %ymm4, %ymm4
|
||||
; AVX2-NEXT: vmovaps (%rdi), %xmm0
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 16(%rdi), %xmm1
|
||||
; AVX2-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm5 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm4 = xmm5[0,1],xmm4[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm4[0,1,2,3],ymm3[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm3 = [21474836481,21474836481,21474836481,21474836481]
|
||||
; AVX2-NEXT: vpermps %ymm6, %ymm3, %ymm4
|
||||
; AVX2-NEXT: vmovaps %ymm6, %ymm2
|
||||
; AVX2-NEXT: vmovups %ymm6, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps %ymm9, %ymm1
|
||||
; AVX2-NEXT: vmovups %ymm9, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm9, %ymm3, %ymm5
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1,2,3,4,5],ymm4[6,7]
|
||||
; AVX2-NEXT: vmovaps 256(%rdi), %ymm0
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 304(%rdi), %xmm4
|
||||
; AVX2-NEXT: vmovaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 288(%rdi), %xmm6
|
||||
; AVX2-NEXT: vmovaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm6 = xmm6[0],xmm4[0],xmm6[1],xmm4[1]
|
||||
; AVX2-NEXT: vmovaps {{.*#+}} xmm4 = <1,5,u,u>
|
||||
; AVX2-NEXT: vpermps %ymm0, %ymm4, %ymm7
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm6 = xmm7[0,1],xmm6[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm5[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm10, %ymm3, %ymm5
|
||||
; AVX2-NEXT: vpermps %ymm8, %ymm3, %ymm6
|
||||
; AVX2-NEXT: vmovaps %ymm8, %ymm7
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm8 = ymm6[0,1,2,3,4,5],ymm5[6,7]
|
||||
; AVX2-NEXT: vmovaps 128(%rdi), %ymm0
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 176(%rdi), %xmm6
|
||||
; AVX2-NEXT: vmovaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 160(%rdi), %xmm5
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm13 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
|
||||
; AVX2-NEXT: vpermps %ymm0, %ymm4, %ymm9
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm6 = xmm9[0,1],xmm13[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm8[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm11, %ymm3, %ymm6
|
||||
; AVX2-NEXT: vpermps %ymm15, %ymm3, %ymm8
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm9 = ymm8[0,1,2,3,4,5],ymm6[6,7]
|
||||
; AVX2-NEXT: vmovaps (%rdi), %ymm13
|
||||
; AVX2-NEXT: vmovups %ymm13, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %xmm6
|
||||
; AVX2-NEXT: vmovaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 48(%rdi), %xmm0
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm8 = xmm6[0],xmm0[0],xmm6[1],xmm0[1]
|
||||
; AVX2-NEXT: vpermps %ymm13, %ymm4, %ymm13
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm0 = xmm13[0,1],xmm8[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm9[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps %ymm14, %ymm9
|
||||
; AVX2-NEXT: vpermps %ymm14, %ymm3, %ymm0
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm8 # 32-byte Reload
|
||||
; AVX2-NEXT: vpermps %ymm8, %ymm3, %ymm3
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vmovaps 384(%rdi), %ymm3
|
||||
; AVX2-NEXT: vmovups %ymm3, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm3, %ymm4, %ymm13
|
||||
; AVX2-NEXT: vmovaps 432(%rdi), %xmm4
|
||||
; AVX2-NEXT: vmovaps 416(%rdi), %xmm3
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm14 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm13 = xmm13[0,1],xmm14[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm13[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm0 = [25769803778,25769803778,25769803778,25769803778]
|
||||
; AVX2-NEXT: vpermps %ymm2, %ymm0, %ymm13
|
||||
; AVX2-NEXT: vpermps %ymm1, %ymm0, %ymm14
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm13 = ymm14[0,1,2,3,4,5],ymm13[6,7]
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX2-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm14 # 16-byte Folded Reload
|
||||
; AVX2-NEXT: # xmm14 = xmm1[2],mem[2],xmm1[3],mem[3]
|
||||
; AVX2-NEXT: vmovaps {{.*#+}} xmm1 = <u,u,2,6>
|
||||
; AVX2-NEXT: vpermps %ymm12, %ymm1, %ymm12
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm12 = xmm14[0,1],xmm12[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm12[0,1,2,3],ymm13[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm10, %ymm0, %ymm12
|
||||
; AVX2-NEXT: vpermps %ymm7, %ymm0, %ymm13
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm12 = ymm13[0,1,2,3,4,5],ymm12[6,7]
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX2-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2, %xmm13 # 16-byte Folded Reload
|
||||
; AVX2-NEXT: # xmm13 = xmm2[2],mem[2],xmm2[3],mem[3]
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm14 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm13 = xmm13[0,1],xmm14[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm13[0,1,2,3],ymm12[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermps %ymm9, %ymm0, %ymm12
|
||||
; AVX2-NEXT: vpermps %ymm8, %ymm0, %ymm13
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm12 = ymm13[0,1,2,3,4,5],ymm12[6,7]
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX2-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2, %xmm13 # 16-byte Folded Reload
|
||||
; AVX2-NEXT: # xmm13 = xmm2[2],mem[2],xmm2[3],mem[3]
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm14 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm13 = xmm13[0,1],xmm14[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm14 = ymm13[0,1,2,3],ymm12[4,5,6,7]
|
||||
; AVX2-NEXT: vpermps %ymm11, %ymm0, %ymm12
|
||||
; AVX2-NEXT: vpermps %ymm15, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm12[6,7]
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm1 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX2-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2, %xmm6 # 16-byte Folded Reload
|
||||
; AVX2-NEXT: # xmm6 = xmm2[2],mem[2],xmm2[3],mem[3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm1 = xmm6[0,1],xmm1[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm13 = ymm1[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [30064771075,30064771075,30064771075,30064771075]
|
||||
; AVX2-NEXT: vpermps %ymm10, %ymm6, %ymm0
|
||||
; AVX2-NEXT: vpermps %ymm7, %ymm6, %ymm1
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm5, %xmm1 # 16-byte Folded Reload
|
||||
; AVX2-NEXT: # xmm1 = xmm5[2],mem[2],xmm5[3],mem[3]
|
||||
; AVX2-NEXT: vmovaps {{.*#+}} xmm5 = <3,7,u,u>
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm5, %ymm7 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm1 = xmm7[0,1],xmm1[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX2-NEXT: vpermps %ymm11, %ymm6, %ymm0
|
||||
; AVX2-NEXT: vpermps %ymm15, %ymm6, %ymm2
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3,4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
||||
; AVX2-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2, %xmm2 # 16-byte Folded Reload
|
||||
; AVX2-NEXT: # xmm2 = xmm2[2],mem[2],xmm2[3],mem[3]
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm5, %ymm7 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm2 = xmm7[0,1],xmm2[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX2-NEXT: vpermps %ymm9, %ymm6, %ymm2
|
||||
; AVX2-NEXT: vpermps %ymm8, %ymm6, %ymm7
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm7[0,1,2,3,4,5],ymm2[6,7]
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm3 = xmm3[2],xmm4[2],xmm3[3],xmm4[3]
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm5, %ymm4 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm3 = xmm4[0,1],xmm3[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm6, %ymm3 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm6, %ymm4 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3,4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX2-NEXT: vunpckhps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4, %xmm4 # 16-byte Folded Reload
|
||||
; AVX2-NEXT: # xmm4 = xmm4[2],mem[2],xmm4[3],mem[3]
|
||||
; AVX2-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %ymm5, %ymm5 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: vblendps {{.*#+}} xmm4 = xmm5[0,1],xmm4[2,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3],ymm3[4,5,6,7]
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, (%rsi)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 32(%rsi)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 64(%rsi)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 96(%rsi)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 96(%rdx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, (%rdx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 32(%rdx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 64(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm14, 96(%rcx)
|
||||
; AVX2-NEXT: vmovaps %ymm13, (%rcx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 32(%rcx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm4 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm4, 64(%rcx)
|
||||
; AVX2-NEXT: vmovaps %ymm3, 64(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm2, 96(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm0, (%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm1, 32(%r8)
|
||||
; AVX2-NEXT: addq $696, %rsp # imm = 0x2B8
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: load_i32_stride4_vf32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 128(%rdi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 192(%rdi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 320(%rdi), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 256(%rdi), %zmm5
|
||||
; AVX512-NEXT: vmovdqu64 448(%rdi), %zmm6
|
||||
; AVX512-NEXT: vmovdqu64 384(%rdi), %zmm7
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm8 = [0,4,8,12,16,20,24,28,0,4,8,12,16,20,24,28]
|
||||
; AVX512-NEXT: # zmm8 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm7, %zmm9
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm8, %zmm9
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm10
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm8, %zmm10
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm9 = zmm10[0,1,2,3],zmm9[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm10
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm8, %zmm10
|
||||
; AVX512-NEXT: vpermi2d %zmm1, %zmm0, %zmm8
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm8 = zmm8[0,1,2,3],zmm10[4,5,6,7]
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm10 = [1,5,9,13,17,21,25,29,1,5,9,13,17,21,25,29]
|
||||
; AVX512-NEXT: # zmm10 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm7, %zmm11
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm10, %zmm11
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm12
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm10, %zmm12
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm11 = zmm12[0,1,2,3],zmm11[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm12
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm10, %zmm12
|
||||
; AVX512-NEXT: vpermi2d %zmm1, %zmm0, %zmm10
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm10 = zmm10[0,1,2,3],zmm12[4,5,6,7]
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm12 = [2,6,10,14,18,22,26,30,2,6,10,14,18,22,26,30]
|
||||
; AVX512-NEXT: # zmm12 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm7, %zmm13
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm12, %zmm13
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm14
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm12, %zmm14
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm13 = zmm14[0,1,2,3],zmm13[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm14
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm12, %zmm14
|
||||
; AVX512-NEXT: vpermi2d %zmm1, %zmm0, %zmm12
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm12 = zmm12[0,1,2,3],zmm14[4,5,6,7]
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm14 = [3,7,11,15,19,23,27,31,3,7,11,15,19,23,27,31]
|
||||
; AVX512-NEXT: # zmm14 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm14, %zmm7
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm14, %zmm5
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm4 = zmm5[0,1,2,3],zmm7[4,5,6,7]
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm14, %zmm2
|
||||
; AVX512-NEXT: vpermt2d %zmm1, %zmm14, %zmm0
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm2[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqu64 %zmm9, 64(%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm8, (%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm11, 64(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm10, (%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm13, 64(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm12, (%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm4, 64(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm0, (%r8)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%wide.vec = load <128 x i32>, <128 x i32>* %in.vec, align 32
|
||||
|
||||
%strided.vec0 = shufflevector <128 x i32> %wide.vec, <128 x i32> poison, <32 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60, i32 64, i32 68, i32 72, i32 76, i32 80, i32 84, i32 88, i32 92, i32 96, i32 100, i32 104, i32 108, i32 112, i32 116, i32 120, i32 124>
|
||||
%strided.vec1 = shufflevector <128 x i32> %wide.vec, <128 x i32> poison, <32 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61, i32 65, i32 69, i32 73, i32 77, i32 81, i32 85, i32 89, i32 93, i32 97, i32 101, i32 105, i32 109, i32 113, i32 117, i32 121, i32 125>
|
||||
%strided.vec2 = shufflevector <128 x i32> %wide.vec, <128 x i32> poison, <32 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62, i32 66, i32 70, i32 74, i32 78, i32 82, i32 86, i32 90, i32 94, i32 98, i32 102, i32 106, i32 110, i32 114, i32 118, i32 122, i32 126>
|
||||
%strided.vec3 = shufflevector <128 x i32> %wide.vec, <128 x i32> poison, <32 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63, i32 67, i32 71, i32 75, i32 79, i32 83, i32 87, i32 91, i32 95, i32 99, i32 103, i32 107, i32 111, i32 115, i32 119, i32 123, i32 127>
|
||||
|
||||
store <32 x i32> %strided.vec0, <32 x i32>* %out.vec0, align 32
|
||||
store <32 x i32> %strided.vec1, <32 x i32>* %out.vec1, align 32
|
||||
store <32 x i32> %strided.vec2, <32 x i32>* %out.vec2, align 32
|
||||
store <32 x i32> %strided.vec3, <32 x i32>* %out.vec3, align 32
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
|
|
@ -382,3 +382,346 @@ define void @load_i64_stride2_vf16(<32 x i64>* %in.vec, <16 x i64>* %out.vec0, <
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @load_i64_stride2_vf32(<64 x i64>* %in.vec, <32 x i64>* %out.vec0, <32 x i64>* %out.vec1) nounwind {
|
||||
; SSE-LABEL: load_i64_stride2_vf32:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $152, %rsp
|
||||
; SSE-NEXT: movaps 272(%rdi), %xmm15
|
||||
; SSE-NEXT: movaps 208(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 192(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps 144(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps 128(%rdi), %xmm4
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm13
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 304(%rdi), %xmm14
|
||||
; SSE-NEXT: movaps 288(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps 240(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps 224(%rdi), %xmm11
|
||||
; SSE-NEXT: movaps 176(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps 160(%rdi), %xmm8
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm6
|
||||
; SSE-NEXT: movaps %xmm6, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm6 = xmm6[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm3, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm13[0]
|
||||
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm13[1]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm8, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm7[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm8 = xmm8[1],xmm7[1]
|
||||
; SSE-NEXT: movaps %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm4, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm10[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm10[1]
|
||||
; SSE-NEXT: movaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm11, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm11 = xmm11[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm5, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm9[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm9[1]
|
||||
; SSE-NEXT: movaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm12, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm14[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm14[1]
|
||||
; SSE-NEXT: movaps %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 256(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm0, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm15[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm15[1]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 368(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 352(%rdi), %xmm15
|
||||
; SSE-NEXT: movaps %xmm15, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm15 = xmm15[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 336(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 320(%rdi), %xmm11
|
||||
; SSE-NEXT: movaps %xmm11, %xmm13
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm13 = xmm13[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm11 = xmm11[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 432(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 416(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps %xmm12, %xmm14
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm14 = xmm14[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 400(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 384(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps %xmm5, %xmm3
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 496(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps 480(%rdi), %xmm4
|
||||
; SSE-NEXT: movaps %xmm4, %xmm9
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm9 = xmm9[0],xmm1[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 464(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps 448(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm2[1]
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps %xmm10, %xmm8
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm8 = xmm8[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm2[1]
|
||||
; SSE-NEXT: movaps (%rdi), %xmm7
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps %xmm7, %xmm6
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm6 = xmm6[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm7 = xmm7[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm0, 224(%rsi)
|
||||
; SSE-NEXT: movaps %xmm3, 192(%rsi)
|
||||
; SSE-NEXT: movaps %xmm13, 160(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 128(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%rsi)
|
||||
; SSE-NEXT: movaps (%rsp), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%rsi)
|
||||
; SSE-NEXT: movaps %xmm6, (%rsi)
|
||||
; SSE-NEXT: movaps %xmm9, 240(%rsi)
|
||||
; SSE-NEXT: movaps %xmm14, 208(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 176(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 144(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%rsi)
|
||||
; SSE-NEXT: movaps %xmm8, 16(%rsi)
|
||||
; SSE-NEXT: movaps %xmm1, 224(%rdx)
|
||||
; SSE-NEXT: movaps %xmm4, 240(%rdx)
|
||||
; SSE-NEXT: movaps %xmm5, 192(%rdx)
|
||||
; SSE-NEXT: movaps %xmm12, 208(%rdx)
|
||||
; SSE-NEXT: movaps %xmm11, 160(%rdx)
|
||||
; SSE-NEXT: movaps %xmm15, 176(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 128(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 144(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%rdx)
|
||||
; SSE-NEXT: movaps %xmm7, (%rdx)
|
||||
; SSE-NEXT: movaps %xmm10, 16(%rdx)
|
||||
; SSE-NEXT: addq $152, %rsp
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: load_i64_stride2_vf32:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vmovaps (%rdi), %ymm0
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %ymm1
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %ymm2
|
||||
; AVX1-NEXT: vmovaps 480(%rdi), %ymm3
|
||||
; AVX1-NEXT: vmovaps 448(%rdi), %ymm4
|
||||
; AVX1-NEXT: vmovaps 288(%rdi), %ymm5
|
||||
; AVX1-NEXT: vmovaps 256(%rdi), %ymm6
|
||||
; AVX1-NEXT: vmovaps 352(%rdi), %ymm7
|
||||
; AVX1-NEXT: vmovaps 320(%rdi), %ymm8
|
||||
; AVX1-NEXT: vmovaps 160(%rdi), %ymm9
|
||||
; AVX1-NEXT: vmovaps 128(%rdi), %ymm10
|
||||
; AVX1-NEXT: vmovaps 224(%rdi), %ymm11
|
||||
; AVX1-NEXT: vmovaps 192(%rdi), %ymm12
|
||||
; AVX1-NEXT: vmovaps 416(%rdi), %ymm13
|
||||
; AVX1-NEXT: vmovaps 384(%rdi), %ymm14
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm15 = ymm14[2,3],ymm13[2,3]
|
||||
; AVX1-NEXT: vmovups %ymm15, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm15 = ymm14[0,1],ymm13[0,1]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm14 = ymm12[2,3],ymm11[2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm13 = ymm12[0,1],ymm11[0,1]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm12 = ymm10[2,3],ymm9[2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm11 = ymm10[0,1],ymm9[0,1]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm10 = ymm8[2,3],ymm7[2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm9 = ymm8[0,1],ymm7[0,1]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm8 = ymm6[2,3],ymm5[2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm7 = ymm6[0,1],ymm5[0,1]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm6 = ymm4[2,3],ymm3[2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm5 = ymm4[0,1],ymm3[0,1]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm4 = ymm1[2,3],ymm2[2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[0,1],ymm2[0,1]
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %ymm2
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm0[2,3],ymm2[2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[0,1],ymm2[0,1]
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm13[0],ymm14[0],ymm13[2],ymm14[2]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm13[1],ymm14[1],ymm13[3],ymm14[3]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm14 = ymm11[0],ymm12[0],ymm11[2],ymm12[2]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm11 = ymm11[1],ymm12[1],ymm11[3],ymm12[3]
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm12 = ymm9[0],ymm10[0],ymm9[2],ymm10[2]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm9 = ymm9[1],ymm10[1],ymm9[3],ymm10[3]
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm10 = ymm7[0],ymm8[0],ymm7[2],ymm8[2]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm7 = ymm7[1],ymm8[1],ymm7[3],ymm8[3]
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm8 = ymm5[0],ymm6[0],ymm5[2],ymm6[2]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm5 = ymm5[1],ymm6[1],ymm5[3],ymm6[3]
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm6 = ymm15[0],ymm0[0],ymm15[2],ymm0[2]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm13 = ymm15[1],ymm0[1],ymm15[3],ymm0[3]
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm15 = ymm3[0],ymm4[0],ymm3[2],ymm4[2]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm3 = ymm3[1],ymm4[1],ymm3[3],ymm4[3]
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm4 = ymm2[0],ymm1[0],ymm2[2],ymm1[2]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm2[1],ymm1[1],ymm2[3],ymm1[3]
|
||||
; AVX1-NEXT: vmovaps %ymm8, 224(%rsi)
|
||||
; AVX1-NEXT: vmovaps %ymm10, 128(%rsi)
|
||||
; AVX1-NEXT: vmovaps %ymm12, 160(%rsi)
|
||||
; AVX1-NEXT: vmovaps %ymm14, 64(%rsi)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 96(%rsi)
|
||||
; AVX1-NEXT: vmovaps %ymm4, (%rsi)
|
||||
; AVX1-NEXT: vmovaps %ymm15, 32(%rsi)
|
||||
; AVX1-NEXT: vmovaps %ymm6, 192(%rsi)
|
||||
; AVX1-NEXT: vmovaps %ymm13, 192(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm5, 224(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm7, 128(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm9, 160(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm11, 64(%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm1, 96(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm0, (%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm3, 32(%rdx)
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: load_i64_stride2_vf32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vmovaps (%rdi), %ymm5
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %ymm1
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %ymm2
|
||||
; AVX2-NEXT: vmovaps 480(%rdi), %ymm3
|
||||
; AVX2-NEXT: vmovaps 448(%rdi), %ymm4
|
||||
; AVX2-NEXT: vmovaps 288(%rdi), %ymm6
|
||||
; AVX2-NEXT: vmovaps 256(%rdi), %ymm7
|
||||
; AVX2-NEXT: vmovaps 352(%rdi), %ymm8
|
||||
; AVX2-NEXT: vmovaps 320(%rdi), %ymm9
|
||||
; AVX2-NEXT: vmovaps 160(%rdi), %ymm10
|
||||
; AVX2-NEXT: vmovaps 128(%rdi), %ymm11
|
||||
; AVX2-NEXT: vmovaps 224(%rdi), %ymm12
|
||||
; AVX2-NEXT: vmovaps 192(%rdi), %ymm13
|
||||
; AVX2-NEXT: vmovaps 416(%rdi), %ymm14
|
||||
; AVX2-NEXT: vmovaps 384(%rdi), %ymm15
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm13[0],ymm12[0],ymm13[2],ymm12[2]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm12 = ymm13[1],ymm12[1],ymm13[3],ymm12[3]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm13 = ymm11[0],ymm10[0],ymm11[2],ymm10[2]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm10 = ymm11[1],ymm10[1],ymm11[3],ymm10[3]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm11 = ymm9[0],ymm8[0],ymm9[2],ymm8[2]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm8 = ymm9[1],ymm8[1],ymm9[3],ymm8[3]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm9 = ymm7[0],ymm6[0],ymm7[2],ymm6[2]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm6 = ymm7[1],ymm6[1],ymm7[3],ymm6[3]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm7 = ymm4[0],ymm3[0],ymm4[2],ymm3[2]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm3 = ymm4[1],ymm3[1],ymm4[3],ymm3[3]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm4 = ymm15[0],ymm14[0],ymm15[2],ymm14[2]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm14 = ymm15[1],ymm14[1],ymm15[3],ymm14[3]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm15 = ymm1[0],ymm2[0],ymm1[2],ymm2[2]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm1 = ymm1[1],ymm2[1],ymm1[3],ymm2[3]
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %ymm2
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm5[0],ymm2[0],ymm5[2],ymm2[2]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm2 = ymm5[1],ymm2[1],ymm5[3],ymm2[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm5 = ymm7[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm5, 224(%rsi)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm5 = ymm9[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm5, 128(%rsi)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm5 = ymm11[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm5, 160(%rsi)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm5 = ymm13[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm5, 64(%rsi)
|
||||
; AVX2-NEXT: vpermpd $216, {{[-0-9]+}}(%r{{[sb]}}p), %ymm5 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: # ymm5 = mem[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm5, 96(%rsi)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, (%rsi)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm15[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 32(%rsi)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm4[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 192(%rsi)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm14[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 192(%rdx)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm3[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 224(%rdx)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm6[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 128(%rdx)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm8[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 160(%rdx)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm10[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 64(%rdx)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm12[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 96(%rdx)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm2[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, (%rdx)
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm1[0,2,1,3]
|
||||
; AVX2-NEXT: vmovaps %ymm0, 32(%rdx)
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: load_i64_stride2_vf32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 128(%rdi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 192(%rdi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 448(%rdi), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 384(%rdi), %zmm5
|
||||
; AVX512-NEXT: vmovdqu64 320(%rdi), %zmm6
|
||||
; AVX512-NEXT: vmovdqu64 256(%rdi), %zmm7
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm8 = [0,2,4,6,8,10,12,14]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm7, %zmm9
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm8, %zmm9
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm10
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm8, %zmm10
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm11
|
||||
; AVX512-NEXT: vpermt2q %zmm3, %zmm8, %zmm11
|
||||
; AVX512-NEXT: vpermi2q %zmm1, %zmm0, %zmm8
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm12 = [1,3,5,7,9,11,13,15]
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm12, %zmm5
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm12, %zmm7
|
||||
; AVX512-NEXT: vpermt2q %zmm3, %zmm12, %zmm2
|
||||
; AVX512-NEXT: vpermt2q %zmm1, %zmm12, %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 %zmm10, 192(%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm8, (%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm11, 64(%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm9, 128(%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm7, 128(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm5, 192(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm0, (%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm2, 64(%rdx)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%wide.vec = load <64 x i64>, <64 x i64>* %in.vec, align 32
|
||||
|
||||
%strided.vec0 = shufflevector <64 x i64> %wide.vec, <64 x i64> poison, <32 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30, i32 32, i32 34, i32 36, i32 38, i32 40, i32 42, i32 44, i32 46, i32 48, i32 50, i32 52, i32 54, i32 56, i32 58, i32 60, i32 62>
|
||||
%strided.vec1 = shufflevector <64 x i64> %wide.vec, <64 x i64> poison, <32 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31, i32 33, i32 35, i32 37, i32 39, i32 41, i32 43, i32 45, i32 47, i32 49, i32 51, i32 53, i32 55, i32 57, i32 59, i32 61, i32 63>
|
||||
|
||||
store <32 x i64> %strided.vec0, <32 x i64>* %out.vec0, align 32
|
||||
store <32 x i64> %strided.vec1, <32 x i64>* %out.vec1, align 32
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
|
|
@ -410,3 +410,522 @@ define void @load_i64_stride4_vf8(<32 x i64>* %in.vec, <8 x i64>* %out.vec0, <8
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @load_i64_stride4_vf16(<64 x i64>* %in.vec, <16 x i64>* %out.vec0, <16 x i64>* %out.vec1, <16 x i64>* %out.vec2, <16 x i64>* %out.vec3) nounwind {
|
||||
; SSE-LABEL: load_i64_stride4_vf16:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $152, %rsp
|
||||
; SSE-NEXT: movaps (%rdi), %xmm8
|
||||
; SSE-NEXT: movaps 416(%rdi), %xmm13
|
||||
; SSE-NEXT: movaps 384(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps 288(%rdi), %xmm15
|
||||
; SSE-NEXT: movaps 256(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 160(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps 128(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps 480(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 448(%rdi), %xmm11
|
||||
; SSE-NEXT: movaps 352(%rdi), %xmm4
|
||||
; SSE-NEXT: movaps 320(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps 224(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps 192(%rdi), %xmm14
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm6
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm0, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm6[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm6[1]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm14, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm5[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm5[1]
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm12, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm4[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm4[1]
|
||||
; SSE-NEXT: movaps %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm11, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm3[0]
|
||||
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm11 = xmm11[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm10, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm9, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm15[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm9 = xmm9[1],xmm15[1]
|
||||
; SSE-NEXT: movaps %xmm9, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm7, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm13[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm7 = xmm7[1],xmm13[1]
|
||||
; SSE-NEXT: movaps %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm8, %xmm15
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm15 = xmm15[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm8 = xmm8[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 240(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 208(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps %xmm12, %xmm14
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm14 = xmm14[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 368(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 336(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps %xmm10, %xmm13
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm13 = xmm13[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 496(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 464(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps %xmm9, %xmm11
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm11 = xmm11[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm9 = xmm9[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 176(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 144(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps %xmm7, %xmm8
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm8 = xmm8[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm7 = xmm7[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 304(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 272(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps %xmm5, %xmm6
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm6 = xmm6[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 432(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 400(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm1, %xmm3
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm2, %xmm4
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm4 = xmm4[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%rsi)
|
||||
; SSE-NEXT: movaps %xmm15, (%rsi)
|
||||
; SSE-NEXT: movaps (%rsp), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%rsi)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, (%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%rdx)
|
||||
; SSE-NEXT: movaps %xmm3, 96(%rcx)
|
||||
; SSE-NEXT: movaps %xmm6, 64(%rcx)
|
||||
; SSE-NEXT: movaps %xmm8, 32(%rcx)
|
||||
; SSE-NEXT: movaps %xmm4, (%rcx)
|
||||
; SSE-NEXT: movaps %xmm11, 112(%rcx)
|
||||
; SSE-NEXT: movaps %xmm13, 80(%rcx)
|
||||
; SSE-NEXT: movaps %xmm14, 48(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%rcx)
|
||||
; SSE-NEXT: movaps %xmm1, 96(%r8)
|
||||
; SSE-NEXT: movaps %xmm5, 64(%r8)
|
||||
; SSE-NEXT: movaps %xmm7, 32(%r8)
|
||||
; SSE-NEXT: movaps %xmm2, (%r8)
|
||||
; SSE-NEXT: movaps %xmm9, 112(%r8)
|
||||
; SSE-NEXT: movaps %xmm10, 80(%r8)
|
||||
; SSE-NEXT: movaps %xmm12, 48(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%r8)
|
||||
; SSE-NEXT: addq $152, %rsp
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: load_i64_stride4_vf16:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: subq $296, %rsp # imm = 0x128
|
||||
; AVX1-NEXT: vmovaps 224(%rdi), %xmm8
|
||||
; AVX1-NEXT: vmovaps 192(%rdi), %xmm9
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm9[0],xmm8[0]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %xmm10
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %xmm11
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm11[0],xmm10[0]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 352(%rdi), %xmm4
|
||||
; AVX1-NEXT: vmovaps 320(%rdi), %xmm5
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm5[0],xmm4[0]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 160(%rdi), %xmm12
|
||||
; AVX1-NEXT: vmovaps 128(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm1[0],xmm12[0]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps (%rdi), %xmm3
|
||||
; AVX1-NEXT: vmovaps 288(%rdi), %xmm6
|
||||
; AVX1-NEXT: vmovaps 256(%rdi), %xmm0
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm4 = xmm5[1],xmm4[1]
|
||||
; AVX1-NEXT: vmovaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm4 = xmm0[0],xmm6[0]
|
||||
; AVX1-NEXT: vmovaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm0[1],xmm6[1]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm3[0],xmm2[0]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm9[1],xmm8[1]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 416(%rdi), %xmm0
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm1 = xmm1[1],xmm12[1]
|
||||
; AVX1-NEXT: vmovaps %xmm1, (%rsp) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 480(%rdi), %xmm1
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm4 = xmm11[1],xmm10[1]
|
||||
; AVX1-NEXT: vmovaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 448(%rdi), %xmm4
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm3[1],xmm2[1]
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm2 = xmm4[0],xmm1[0]
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm1 = xmm4[1],xmm1[1]
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 384(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm2 = xmm1[0],xmm0[0]
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm1[1],xmm0[1]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 224(%rdi), %ymm13
|
||||
; AVX1-NEXT: vmovaps 192(%rdi), %ymm12
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm2 = ymm12[0],ymm13[0],ymm12[2],ymm13[2]
|
||||
; AVX1-NEXT: vmovaps 176(%rdi), %xmm11
|
||||
; AVX1-NEXT: vmovaps 144(%rdi), %xmm10
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm5 = xmm10[0],xmm11[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm5[0,1,2,3],ymm2[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 352(%rdi), %ymm0
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 320(%rdi), %ymm1
|
||||
; AVX1-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm6 = ymm1[0],ymm0[0],ymm1[2],ymm0[2]
|
||||
; AVX1-NEXT: vmovaps 304(%rdi), %xmm15
|
||||
; AVX1-NEXT: vmovaps 272(%rdi), %xmm14
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm9 = xmm14[0],xmm15[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm9[0,1,2,3],ymm6[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 480(%rdi), %ymm8
|
||||
; AVX1-NEXT: vmovaps 448(%rdi), %ymm7
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm6 = ymm7[0],ymm8[0],ymm7[2],ymm8[2]
|
||||
; AVX1-NEXT: vmovaps 432(%rdi), %xmm5
|
||||
; AVX1-NEXT: vmovaps 400(%rdi), %xmm4
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm9 = xmm4[0],xmm5[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm9[0,1,2,3],ymm6[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %ymm3
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %ymm2
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm6 = ymm2[0],ymm3[0],ymm2[2],ymm3[2]
|
||||
; AVX1-NEXT: vmovaps 48(%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps 16(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm9 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm9[0,1,2,3],ymm6[4,5,6,7]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm9 = ymm12[1],ymm13[1],ymm12[3],ymm13[3]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm10 = xmm10[1],xmm11[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm10 = ymm10[0,1,2,3],ymm9[4,5,6,7]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm2 = ymm2[1],ymm3[1],ymm2[3],ymm3[3]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm2[4,5,6,7]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm1 = ymm7[1],ymm8[1],ymm7[3],ymm8[3]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm4[1],xmm5[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1,2,3],ymm1[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
||||
; AVX1-NEXT: vunpckhpd {{[-0-9]+}}(%r{{[sb]}}p), %ymm2, %ymm2 # 32-byte Folded Reload
|
||||
; AVX1-NEXT: # ymm2 = ymm2[1],mem[1],ymm2[3],mem[3]
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm14[1],xmm15[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 112(%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 96(%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 64(%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, (%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 32(%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 80(%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 16(%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 48(%rsi)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 96(%rdx)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 112(%rdx)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, (%rdx)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 16(%rdx)
|
||||
; AVX1-NEXT: vmovaps (%rsp), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 32(%rdx)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 48(%rdx)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 64(%rdx)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm3, 80(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm6, (%rcx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm3, 96(%rcx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm3, 64(%rcx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm3, 32(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm2, 64(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm1, 96(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm0, (%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm10, 32(%r8)
|
||||
; AVX1-NEXT: addq $296, %rsp # imm = 0x128
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: load_i64_stride4_vf16:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: subq $296, %rsp # imm = 0x128
|
||||
; AVX2-NEXT: vmovaps 224(%rdi), %xmm11
|
||||
; AVX2-NEXT: vmovaps 192(%rdi), %xmm15
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm0 = xmm15[0],xmm11[0]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %xmm7
|
||||
; AVX2-NEXT: vmovaps (%rdi), %xmm9
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %xmm4
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm0 = xmm4[0],xmm7[0]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 352(%rdi), %xmm8
|
||||
; AVX2-NEXT: vmovaps 320(%rdi), %xmm6
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm0 = xmm6[0],xmm8[0]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 160(%rdi), %xmm3
|
||||
; AVX2-NEXT: vmovaps 128(%rdi), %xmm2
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm0 = xmm2[0],xmm3[0]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 288(%rdi), %xmm1
|
||||
; AVX2-NEXT: vmovaps 256(%rdi), %xmm5
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm0 = xmm5[0],xmm1[0]
|
||||
; AVX2-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm6[1],xmm8[1]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 416(%rdi), %xmm0
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm1 = xmm5[1],xmm1[1]
|
||||
; AVX2-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 384(%rdi), %xmm1
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm5 = xmm15[1],xmm11[1]
|
||||
; AVX2-NEXT: vmovaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 480(%rdi), %xmm11
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm2[1],xmm3[1]
|
||||
; AVX2-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 448(%rdi), %xmm2
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm4[1],xmm7[1]
|
||||
; AVX2-NEXT: vmovaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm3 = xmm2[0],xmm11[0]
|
||||
; AVX2-NEXT: vmovaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm2[1],xmm11[1]
|
||||
; AVX2-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm2 = xmm1[0],xmm0[0]
|
||||
; AVX2-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm1[1],xmm0[1]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %xmm0
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm1 = xmm9[0],xmm0[0]
|
||||
; AVX2-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm9[1],xmm0[1]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 160(%rdi), %ymm9
|
||||
; AVX2-NEXT: vmovaps 128(%rdi), %ymm8
|
||||
; AVX2-NEXT: vmovaps 224(%rdi), %ymm5
|
||||
; AVX2-NEXT: vmovaps 192(%rdi), %ymm4
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm4[0],ymm5[0],ymm4[2],ymm5[2]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm11 = ymm8[0],ymm9[0],ymm8[2],ymm9[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm11[2,3],ymm0[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 288(%rdi), %ymm0
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 256(%rdi), %ymm1
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 352(%rdi), %ymm14
|
||||
; AVX2-NEXT: vmovaps 320(%rdi), %ymm13
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm11 = ymm13[0],ymm14[0],ymm13[2],ymm14[2]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm15 = ymm1[0],ymm0[0],ymm1[2],ymm0[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm15[2,3],ymm11[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 416(%rdi), %ymm10
|
||||
; AVX2-NEXT: vmovaps 384(%rdi), %ymm7
|
||||
; AVX2-NEXT: vmovaps 480(%rdi), %ymm6
|
||||
; AVX2-NEXT: vmovaps 448(%rdi), %ymm3
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm15 = ymm3[0],ymm6[0],ymm3[2],ymm6[2]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm11 = ymm7[0],ymm10[0],ymm7[2],ymm10[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm11[2,3],ymm15[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %ymm11
|
||||
; AVX2-NEXT: vmovaps (%rdi), %ymm2
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %ymm1
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %ymm0
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm12 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm15 = ymm2[0],ymm11[0],ymm2[2],ymm11[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm12 = ymm15[2,3],ymm12[2,3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm4 = ymm4[1],ymm5[1],ymm4[3],ymm5[3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm5 = ymm8[1],ymm9[1],ymm8[3],ymm9[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm5 = ymm5[2,3],ymm4[2,3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm1 = ymm2[1],ymm11[1],ymm2[3],ymm11[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm1[2,3],ymm0[2,3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm1 = ymm3[1],ymm6[1],ymm3[3],ymm6[3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm2 = ymm7[1],ymm10[1],ymm7[3],ymm10[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm2[2,3],ymm1[2,3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm2 = ymm13[1],ymm14[1],ymm13[3],ymm14[3]
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX2-NEXT: vunpckhpd {{[-0-9]+}}(%r{{[sb]}}p), %ymm3, %ymm3 # 32-byte Folded Reload
|
||||
; AVX2-NEXT: # ymm3 = ymm3[1],mem[1],ymm3[3],mem[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm3[2,3],ymm2[2,3]
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 112(%rsi)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 96(%rsi)
|
||||
; AVX2-NEXT: vmovaps (%rsp), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 64(%rsi)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, (%rsi)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 32(%rsi)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 80(%rsi)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 16(%rsi)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 48(%rsi)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 96(%rdx)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 112(%rdx)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, (%rdx)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 16(%rdx)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 32(%rdx)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 48(%rdx)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 64(%rdx)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm3, 80(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm12, (%rcx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm3, 96(%rcx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm3, 64(%rcx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm3, 32(%rcx)
|
||||
; AVX2-NEXT: vmovaps %ymm2, 64(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm1, 96(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm0, (%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm5, 32(%r8)
|
||||
; AVX2-NEXT: addq $296, %rsp # imm = 0x128
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: load_i64_stride4_vf16:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 128(%rdi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 192(%rdi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 320(%rdi), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 256(%rdi), %zmm5
|
||||
; AVX512-NEXT: vmovdqu64 448(%rdi), %zmm6
|
||||
; AVX512-NEXT: vmovdqu64 384(%rdi), %zmm7
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm8 = [0,4,8,12,0,4,8,12]
|
||||
; AVX512-NEXT: # zmm8 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm7, %zmm9
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm8, %zmm9
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm10
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm8, %zmm10
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm9 = zmm10[0,1,2,3],zmm9[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm10
|
||||
; AVX512-NEXT: vpermt2q %zmm3, %zmm8, %zmm10
|
||||
; AVX512-NEXT: vpermi2q %zmm1, %zmm0, %zmm8
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm8 = zmm8[0,1,2,3],zmm10[4,5,6,7]
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm10 = [1,5,9,13,1,5,9,13]
|
||||
; AVX512-NEXT: # zmm10 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm7, %zmm11
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm10, %zmm11
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm12
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm10, %zmm12
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm11 = zmm12[0,1,2,3],zmm11[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm12
|
||||
; AVX512-NEXT: vpermt2q %zmm3, %zmm10, %zmm12
|
||||
; AVX512-NEXT: vpermi2q %zmm1, %zmm0, %zmm10
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm10 = zmm10[0,1,2,3],zmm12[4,5,6,7]
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm12 = [2,6,10,14,2,6,10,14]
|
||||
; AVX512-NEXT: # zmm12 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm7, %zmm13
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm12, %zmm13
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm14
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm12, %zmm14
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm13 = zmm14[0,1,2,3],zmm13[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm14
|
||||
; AVX512-NEXT: vpermt2q %zmm3, %zmm12, %zmm14
|
||||
; AVX512-NEXT: vpermi2q %zmm1, %zmm0, %zmm12
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm12 = zmm12[0,1,2,3],zmm14[4,5,6,7]
|
||||
; AVX512-NEXT: vbroadcasti64x4 {{.*#+}} zmm14 = [3,7,11,15,3,7,11,15]
|
||||
; AVX512-NEXT: # zmm14 = mem[0,1,2,3,0,1,2,3]
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm14, %zmm7
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm14, %zmm5
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm4 = zmm5[0,1,2,3],zmm7[4,5,6,7]
|
||||
; AVX512-NEXT: vpermt2q %zmm3, %zmm14, %zmm2
|
||||
; AVX512-NEXT: vpermt2q %zmm1, %zmm14, %zmm0
|
||||
; AVX512-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3],zmm2[4,5,6,7]
|
||||
; AVX512-NEXT: vmovdqu64 %zmm9, 64(%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm8, (%rsi)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm11, 64(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm10, (%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm13, 64(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm12, (%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm4, 64(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm0, (%r8)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%wide.vec = load <64 x i64>, <64 x i64>* %in.vec, align 32
|
||||
|
||||
%strided.vec0 = shufflevector <64 x i64> %wide.vec, <64 x i64> poison, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
|
||||
%strided.vec1 = shufflevector <64 x i64> %wide.vec, <64 x i64> poison, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
|
||||
%strided.vec2 = shufflevector <64 x i64> %wide.vec, <64 x i64> poison, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
|
||||
%strided.vec3 = shufflevector <64 x i64> %wide.vec, <64 x i64> poison, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
|
||||
|
||||
store <16 x i64> %strided.vec0, <16 x i64>* %out.vec0, align 32
|
||||
store <16 x i64> %strided.vec1, <16 x i64>* %out.vec1, align 32
|
||||
store <16 x i64> %strided.vec2, <16 x i64>* %out.vec2, align 32
|
||||
store <16 x i64> %strided.vec3, <16 x i64>* %out.vec3, align 32
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -715,3 +715,658 @@ define void @store_i32_stride3_vf16(<16 x i32>* %in.vecptr0, <16 x i32>* %in.vec
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @store_i32_stride3_vf32(<32 x i32>* %in.vecptr0, <32 x i32>* %in.vecptr1, <32 x i32>* %in.vecptr2, <96 x i32>* %out.vec) nounwind {
|
||||
; SSE-LABEL: store_i32_stride3_vf32:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $56, %rsp
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps (%rdi), %xmm2
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm8
|
||||
; SSE-NEXT: movaps (%rsi), %xmm7
|
||||
; SSE-NEXT: movaps 16(%rsi), %xmm3
|
||||
; SSE-NEXT: movaps 32(%rsi), %xmm5
|
||||
; SSE-NEXT: movaps 48(%rsi), %xmm6
|
||||
; SSE-NEXT: movaps (%rdx), %xmm1
|
||||
; SSE-NEXT: movaps 16(%rdx), %xmm11
|
||||
; SSE-NEXT: movaps 32(%rdx), %xmm13
|
||||
; SSE-NEXT: movaps 48(%rdx), %xmm14
|
||||
; SSE-NEXT: movaps %xmm1, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm2[1,3]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm4
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,1],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm2, %xmm0
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm7[1]
|
||||
; SSE-NEXT: movaps %xmm1, %xmm4
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm4 = xmm4[1,0],xmm7[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm4 = xmm4[2,0],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm7 = xmm7[3,3],xmm1[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,3],xmm7[0,2]
|
||||
; SSE-NEXT: movaps %xmm1, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm11, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm10[1,3]
|
||||
; SSE-NEXT: movaps %xmm10, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,1],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm10, %xmm0
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm11, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,0],xmm3[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[2,0],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[3,3],xmm11[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm11 = xmm11[2],xmm10[2],xmm11[3],xmm10[3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm11 = xmm11[0,3],xmm3[0,2]
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm13, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm9[1,3]
|
||||
; SSE-NEXT: movaps %xmm9, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,1],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm9, %xmm0
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm5[1]
|
||||
; SSE-NEXT: movaps %xmm13, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,0],xmm5[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[2,0],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm5 = xmm5[3,3],xmm13[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm13 = xmm13[2],xmm9[2],xmm13[3],xmm9[3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm13 = xmm13[0,3],xmm5[0,2]
|
||||
; SSE-NEXT: movaps %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm14, %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm8[1,3]
|
||||
; SSE-NEXT: movaps %xmm8, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm6[0],xmm2[1],xmm6[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,1],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm8, %xmm0
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm6[1]
|
||||
; SSE-NEXT: movaps %xmm14, %xmm15
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm15 = xmm15[1,0],xmm6[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm15 = xmm15[2,0],xmm0[0,2]
|
||||
; SSE-NEXT: movaps 64(%rsi), %xmm0
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[3,3],xmm14[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm14 = xmm14[2],xmm8[2],xmm14[3],xmm8[3]
|
||||
; SSE-NEXT: movaps 64(%rdx), %xmm10
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm14 = xmm14[0,3],xmm6[0,2]
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm10, %xmm1
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm12[1,3]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm14
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm14 = xmm14[0],xmm0[0],xmm14[1],xmm0[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm14 = xmm14[0,1],xmm1[0,2]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm1
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm10, %xmm13
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm13 = xmm13[1,0],xmm0[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm13 = xmm13[2,0],xmm1[0,2]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3],xmm10[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm10 = xmm10[2],xmm12[2],xmm10[3],xmm12[3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm10 = xmm10[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 80(%rdx), %xmm12
|
||||
; SSE-NEXT: movaps %xmm12, %xmm1
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm3[1,3]
|
||||
; SSE-NEXT: movaps 80(%rsi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm3, %xmm11
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm11 = xmm11[0],xmm0[0],xmm11[1],xmm0[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm11 = xmm11[0,1],xmm1[0,2]
|
||||
; SSE-NEXT: movaps %xmm3, %xmm1
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm9
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm9 = xmm9[1,0],xmm0[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm9 = xmm9[2,0],xmm1[0,2]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3],xmm12[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm12 = xmm12[2],xmm3[2],xmm12[3],xmm3[3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm12 = xmm12[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 96(%rdx), %xmm6
|
||||
; SSE-NEXT: movaps %xmm6, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,1],xmm3[1,3]
|
||||
; SSE-NEXT: movaps 96(%rsi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm3, %xmm8
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm8 = xmm8[0],xmm0[0],xmm8[1],xmm0[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,1],xmm2[0,2]
|
||||
; SSE-NEXT: movaps %xmm3, %xmm2
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm6, %xmm7
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm7 = xmm7[1,0],xmm0[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm7 = xmm7[2,0],xmm2[0,2]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3],xmm6[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm6 = xmm6[2],xmm3[2],xmm6[3],xmm3[3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps 112(%rdx), %xmm2
|
||||
; SSE-NEXT: movaps %xmm2, %xmm3
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,1],xmm5[1,3]
|
||||
; SSE-NEXT: movaps 112(%rsi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm5, %xmm4
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,1],xmm3[0,2]
|
||||
; SSE-NEXT: movaps %xmm5, %xmm3
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm1
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,0],xmm0[1,0]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm3[0,2]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3],xmm2[3,3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm2 = xmm2[2],xmm5[2],xmm2[3],xmm5[3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,3],xmm0[0,2]
|
||||
; SSE-NEXT: movaps %xmm2, 368(%rcx)
|
||||
; SSE-NEXT: movaps %xmm1, 352(%rcx)
|
||||
; SSE-NEXT: movaps %xmm4, 336(%rcx)
|
||||
; SSE-NEXT: movaps %xmm6, 320(%rcx)
|
||||
; SSE-NEXT: movaps %xmm7, 304(%rcx)
|
||||
; SSE-NEXT: movaps %xmm8, 288(%rcx)
|
||||
; SSE-NEXT: movaps %xmm12, 272(%rcx)
|
||||
; SSE-NEXT: movaps %xmm9, 256(%rcx)
|
||||
; SSE-NEXT: movaps %xmm11, 240(%rcx)
|
||||
; SSE-NEXT: movaps %xmm10, 224(%rcx)
|
||||
; SSE-NEXT: movaps %xmm13, 208(%rcx)
|
||||
; SSE-NEXT: movaps %xmm14, 192(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 176(%rcx)
|
||||
; SSE-NEXT: movaps %xmm15, 160(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 144(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 128(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%rcx)
|
||||
; SSE-NEXT: movaps (%rsp), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%rcx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, (%rcx)
|
||||
; SSE-NEXT: addq $56, %rsp
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: store_i32_stride3_vf32:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vmovaps (%rsi), %xmm0
|
||||
; AVX1-NEXT: vmovaps (%rdi), %xmm1
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %xmm5
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %xmm4
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm1[1],xmm0[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm0[1,1],xmm2[0,2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[2,0],xmm1[2,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vbroadcastsd (%rdx), %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm8 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps 80(%rdx), %xmm1
|
||||
; AVX1-NEXT: vmovaps 80(%rsi), %xmm2
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm2[3,0],xmm1[3,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm1[2,1],xmm3[0,2]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[1,0],xmm2[1,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[2,0],xmm2[2,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vbroadcastsd 88(%rdi), %ymm2
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm9 = ymm1[0,1],ymm2[2],ymm1[3,4],ymm2[5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovaps 48(%rdx), %xmm2
|
||||
; AVX1-NEXT: vmovaps 48(%rsi), %xmm3
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm6 = xmm3[3,0],xmm2[3,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm6 = xmm2[2,1],xmm6[0,2]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[1,0],xmm3[1,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[2,0],xmm3[2,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm2, %ymm2
|
||||
; AVX1-NEXT: vbroadcastsd 56(%rdi), %ymm3
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
||||
; AVX1-NEXT: vmovaps 112(%rdx), %xmm3
|
||||
; AVX1-NEXT: vmovaps 112(%rsi), %xmm6
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm6[3,0],xmm3[3,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm3[2,1],xmm7[0,2]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm3[1,0],xmm6[1,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm3[2,0],xmm6[2,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm3, %ymm3
|
||||
; AVX1-NEXT: vbroadcastsd 120(%rdi), %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1],ymm6[2],ymm3[3,4],ymm6[5],ymm3[6,7]
|
||||
; AVX1-NEXT: vmovaps 64(%rsi), %xmm6
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm7 = xmm4[1],xmm6[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm6[1,1],xmm7[0,2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm6 = xmm6[0],xmm4[0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm4 = xmm6[2,0],xmm4[2,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm4, %ymm4
|
||||
; AVX1-NEXT: vbroadcastsd 64(%rdx), %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm4 = ymm4[0,1],ymm6[2],ymm4[3,4],ymm6[5],ymm4[6,7]
|
||||
; AVX1-NEXT: vmovaps 32(%rsi), %xmm6
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm7 = xmm5[1],xmm6[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm6[1,1],xmm7[0,2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm6 = xmm6[0],xmm5[0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm5 = xmm6[2,0],xmm5[2,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm5, %ymm5
|
||||
; AVX1-NEXT: vbroadcastsd 32(%rdx), %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1],ymm6[2],ymm5[3,4],ymm6[5],ymm5[6,7]
|
||||
; AVX1-NEXT: vmovaps 96(%rsi), %xmm6
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %xmm7
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm7[1],xmm6[1]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm6[1,1],xmm0[0,2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm6 = xmm6[0],xmm7[0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm6 = xmm6[2,0],xmm7[2,1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm6, %ymm0
|
||||
; AVX1-NEXT: vbroadcastsd 96(%rdx), %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm6 = ymm0[0,1],ymm6[2],ymm0[3,4],ymm6[5],ymm0[6,7]
|
||||
; AVX1-NEXT: vmovaps 16(%rdx), %xmm0
|
||||
; AVX1-NEXT: vmovaps 16(%rsi), %xmm7
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm7[3,0],xmm0[3,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm0[2,1],xmm1[0,2]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,0],xmm7[1,0]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[2,0],xmm7[2,2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vbroadcastsd 24(%rdi), %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm1 = mem[1,0,2,2]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm7 = mem[1,1,2,2]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm7[0],ymm1[1],ymm7[2,3],ymm1[4],ymm7[5,6],ymm1[7]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} ymm7 = mem[0,0,3,3,4,4,7,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1],ymm7[2],ymm1[3,4],ymm7[5],ymm1[6,7]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm7 = mem[1,0,2,2]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm10 = mem[1,1,2,2]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm7 = ymm10[0],ymm7[1],ymm10[2,3],ymm7[4],ymm10[5,6],ymm7[7]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} ymm10 = mem[0,0,3,3,4,4,7,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm7 = ymm7[0,1],ymm10[2],ymm7[3,4],ymm10[5],ymm7[6,7]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm10 = mem[1,0,2,2]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm11 = mem[1,1,2,2]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm10 = ymm11[0],ymm10[1],ymm11[2,3],ymm10[4],ymm11[5,6],ymm10[7]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} ymm11 = mem[0,0,3,3,4,4,7,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm10 = ymm10[0,1],ymm11[2],ymm10[3,4],ymm11[5],ymm10[6,7]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm11 = mem[1,0,2,2]
|
||||
; AVX1-NEXT: vpermilpd {{.*#+}} ymm12 = mem[1,1,2,2]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm11 = ymm12[0],ymm11[1],ymm12[2,3],ymm11[4],ymm12[5,6],ymm11[7]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} ymm12 = mem[0,0,3,3,4,4,7,7]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm11 = ymm11[0,1],ymm12[2],ymm11[3,4],ymm12[5],ymm11[6,7]
|
||||
; AVX1-NEXT: vmovaps %ymm11, 32(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm10, 320(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm7, 128(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm1, 224(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm0, 64(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm6, 288(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm5, 96(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm4, 192(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm3, 352(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm2, 160(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm9, 256(%rcx)
|
||||
; AVX1-NEXT: vmovaps %ymm8, (%rcx)
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: store_i32_stride3_vf32:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: subq $40, %rsp
|
||||
; AVX2-SLOW-NEXT: vmovaps (%rdi), %ymm0
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vmovaps 32(%rdi), %ymm4
|
||||
; AVX2-SLOW-NEXT: vmovaps 64(%rdi), %ymm8
|
||||
; AVX2-SLOW-NEXT: vmovaps 32(%rsi), %ymm5
|
||||
; AVX2-SLOW-NEXT: vmovaps 64(%rsi), %ymm9
|
||||
; AVX2-SLOW-NEXT: vmovaps 96(%rsi), %ymm2
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vmovaps 32(%rdx), %ymm10
|
||||
; AVX2-SLOW-NEXT: vmovaps 64(%rdx), %ymm12
|
||||
; AVX2-SLOW-NEXT: vmovaps 96(%rdx), %ymm6
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm1 = mem[1,0,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,1]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm3 = ymm0[0,0,2,1]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm1 = ymm3[0],ymm1[1],ymm3[2,3],ymm1[4],ymm3[5,6],ymm1[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd (%rdx), %ymm3
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1],ymm3[2],ymm1[3,4],ymm3[5],ymm1[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, (%rsp) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm3 = ymm12[2,1,3,3]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm7 = ymm9[1,2,3,3,5,6,7,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm7 = ymm7[2,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm3 = ymm7[0],ymm3[1],ymm7[2,3],ymm3[4],ymm7[5,6],ymm3[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd 88(%rdi), %ymm7
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1],ymm7[2],ymm3[3,4],ymm7[5],ymm3[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm7 = ymm10[2,1,3,3]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm11 = ymm5[1,2,3,3,5,6,7,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm11 = ymm11[2,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm7 = ymm11[0],ymm7[1],ymm11[2,3],ymm7[4],ymm11[5,6],ymm7[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd 56(%rdi), %ymm11
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm7[0,1],ymm11[2],ymm7[3,4],ymm11[5],ymm7[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm11 = ymm6[2,1,3,3]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm13 = ymm2[1,2,3,3,5,6,7,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm13 = ymm13[2,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm11 = ymm13[0],ymm11[1],ymm13[2,3],ymm11[4],ymm13[5,6],ymm11[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd 120(%rdi), %ymm13
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm11 = ymm11[0,1],ymm13[2],ymm11[3,4],ymm13[5],ymm11[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm13 = mem[1,0,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm13 = ymm13[0,1,0,1]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm14 = ymm8[0,0,2,1]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm13 = ymm14[0],ymm13[1],ymm14[2,3],ymm13[4],ymm14[5,6],ymm13[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd 64(%rdx), %ymm14
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm13 = ymm13[0,1],ymm14[2],ymm13[3,4],ymm14[5],ymm13[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm14 = mem[1,0,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm14 = ymm14[0,1,0,1]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm15 = ymm4[0,0,2,1]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm14 = ymm15[0],ymm14[1],ymm15[2,3],ymm14[4],ymm15[5,6],ymm14[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd 32(%rdx), %ymm15
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm14 = ymm14[0,1],ymm15[2],ymm14[3,4],ymm15[5],ymm14[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm15 = mem[1,0,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm15 = ymm15[0,1,0,1]
|
||||
; AVX2-SLOW-NEXT: vmovaps 96(%rdi), %ymm2
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm1 = ymm2[0,0,2,1]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0],ymm15[1],ymm1[2,3],ymm15[4],ymm1[5,6],ymm15[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd 96(%rdx), %ymm15
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1],ymm15[2],ymm1[3,4],ymm15[5],ymm1[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovaps (%rsi), %ymm15
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm3 = ymm15[1,2,3,3,5,6,7,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[2,2,2,3]
|
||||
; AVX2-SLOW-NEXT: vmovaps (%rdx), %ymm0
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm7 = ymm0[2,1,3,3]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0],ymm7[1],ymm3[2,3],ymm7[4],ymm3[5,6],ymm7[7]
|
||||
; AVX2-SLOW-NEXT: vbroadcastsd 24(%rdi), %ymm7
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1],ymm7[2],ymm3[3,4],ymm7[5],ymm3[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm7 = ymm8[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm8 = ymm12[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm7 = ymm8[0],ymm7[1],ymm8[2,3],ymm7[4],ymm8[5,6],ymm7[7]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm8 = ymm9[0,0,3,3,4,4,7,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm7 = ymm7[0,1],ymm8[2],ymm7[3,4],ymm8[5],ymm7[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm8 = ymm10[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm4 = ymm8[0],ymm4[1],ymm8[2,3],ymm4[4],ymm8[5,6],ymm4[7]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm5 = ymm5[0,0,3,3,4,4,7,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm4 = ymm4[0,1],ymm5[2],ymm4[3,4],ymm5[5],ymm4[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm5 = ymm6[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm2 = ymm5[0],ymm2[1],ymm5[2,3],ymm2[4],ymm5[5,6],ymm2[7]
|
||||
; AVX2-SLOW-NEXT: vpermilps $240, {{[-0-9]+}}(%r{{[sb]}}p), %ymm5 # 32-byte Folded Reload
|
||||
; AVX2-SLOW-NEXT: # ymm5 = mem[0,0,3,3,4,4,7,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm5[2],ymm2[3,4],ymm5[5],ymm2[6,7]
|
||||
; AVX2-SLOW-NEXT: vpermpd $165, {{[-0-9]+}}(%r{{[sb]}}p), %ymm5 # 32-byte Folded Reload
|
||||
; AVX2-SLOW-NEXT: # ymm5 = mem[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm5[1],ymm0[2,3],ymm5[4],ymm0[5,6],ymm5[7]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm5 = ymm15[0,0,3,3,4,4,7,7]
|
||||
; AVX2-SLOW-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm5[2],ymm0[3,4],ymm5[5],ymm0[6,7]
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm0, 32(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm2, 320(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm4, 128(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm7, 224(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm3, 64(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm1, 288(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm14, 96(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm13, 192(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm11, 352(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm0, 160(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm0, 256(%rcx)
|
||||
; AVX2-SLOW-NEXT: vmovups (%rsp), %ymm0 # 32-byte Reload
|
||||
; AVX2-SLOW-NEXT: vmovaps %ymm0, (%rcx)
|
||||
; AVX2-SLOW-NEXT: addq $40, %rsp
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-ALL-LABEL: store_i32_stride3_vf32:
|
||||
; AVX2-FAST-ALL: # %bb.0:
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps (%rdi), %ymm0
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 32(%rdi), %ymm5
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 64(%rdi), %ymm9
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps (%rsi), %ymm1
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 32(%rsi), %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 64(%rsi), %ymm11
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 96(%rsi), %ymm6
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 32(%rdx), %ymm12
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 64(%rdx), %ymm4
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 96(%rdx), %ymm15
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastf128 {{.*#+}} ymm10 = [1,0,2,2,1,0,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: # ymm10 = mem[0,1,0,1]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm10, %ymm2
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm3 = ymm0[0,0,2,1]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2,3],ymm2[4],ymm3[5,6],ymm2[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd (%rdx), %ymm3
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm3 = ymm9[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm8 = ymm4[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm3 = ymm8[0],ymm3[1],ymm8[2,3],ymm3[4],ymm8[5,6],ymm3[7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermilps {{.*#+}} ymm8 = ymm11[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0,1],ymm8[2],ymm3[3,4],ymm8[5],ymm3[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps {{.*#+}} ymm13 = [5,6,5,6,5,6,7,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm11, %ymm13, %ymm8
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[2,1,3,3]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm4 = ymm8[0],ymm4[1],ymm8[2,3],ymm4[4],ymm8[5,6],ymm4[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd 88(%rdi), %ymm8
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm4 = ymm4[0,1],ymm8[2],ymm4[3,4],ymm8[5],ymm4[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm7, %ymm13, %ymm8
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm14 = ymm12[2,1,3,3]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm8 = ymm8[0],ymm14[1],ymm8[2,3],ymm14[4],ymm8[5,6],ymm14[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd 56(%rdi), %ymm14
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm8 = ymm8[0,1],ymm14[2],ymm8[3,4],ymm14[5],ymm8[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm14 = ymm5[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm12 = ymm12[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm12 = ymm12[0],ymm14[1],ymm12[2,3],ymm14[4],ymm12[5,6],ymm14[7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermilps {{.*#+}} ymm14 = ymm7[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm12 = ymm12[0,1],ymm14[2],ymm12[3,4],ymm14[5],ymm12[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm6, %ymm13, %ymm14
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm2 = ymm15[2,1,3,3]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm14[0],ymm2[1],ymm14[2,3],ymm2[4],ymm14[5,6],ymm2[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd 120(%rdi), %ymm14
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm14 = ymm2[0,1],ymm14[2],ymm2[3,4],ymm14[5],ymm2[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm2 = ymm15[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps 96(%rdi), %ymm15
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm3 = ymm15[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0],ymm3[1],ymm2[2,3],ymm3[4],ymm2[5,6],ymm3[7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermilps {{.*#+}} ymm3 = ymm6[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm3[2],ymm2[3,4],ymm3[5],ymm2[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm11, %ymm10, %ymm3
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm9 = ymm9[0,0,2,1]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm3 = ymm9[0],ymm3[1],ymm9[2,3],ymm3[4],ymm9[5,6],ymm3[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd 64(%rdx), %ymm9
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1],ymm9[2],ymm3[3,4],ymm9[5],ymm3[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm7, %ymm10, %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm5 = ymm5[0,0,2,1]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0],ymm7[1],ymm5[2,3],ymm7[4],ymm5[5,6],ymm7[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd 32(%rdx), %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1],ymm7[2],ymm5[3,4],ymm7[5],ymm5[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm6, %ymm10, %ymm6
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps (%rdx), %ymm7
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm9 = ymm15[0,0,2,1]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm6 = ymm9[0],ymm6[1],ymm9[2,3],ymm6[4],ymm9[5,6],ymm6[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd 96(%rdx), %ymm9
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm6 = ymm6[0,1],ymm9[2],ymm6[3,4],ymm9[5],ymm6[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm13, %ymm9
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm10 = ymm7[2,1,3,3]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm9 = ymm9[0],ymm10[1],ymm9[2,3],ymm10[4],ymm9[5,6],ymm10[7]
|
||||
; AVX2-FAST-ALL-NEXT: vbroadcastsd 24(%rdi), %ymm10
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm9 = ymm9[0,1],ymm10[2],ymm9[3,4],ymm10[5],ymm9[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vpermpd {{.*#+}} ymm7 = ymm7[1,1,2,2]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm0 = ymm7[0],ymm0[1],ymm7[2,3],ymm0[4],ymm7[5,6],ymm0[7]
|
||||
; AVX2-FAST-ALL-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-ALL-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3,4],ymm1[5],ymm0[6,7]
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm0, 32(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm9, 64(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm6, 288(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm5, 96(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm3, 192(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm2, 320(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm14, 352(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm12, 128(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm8, 160(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm4, 256(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm0, 224(%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-FAST-ALL-NEXT: vmovaps %ymm0, (%rcx)
|
||||
; AVX2-FAST-ALL-NEXT: vzeroupper
|
||||
; AVX2-FAST-ALL-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-PERLANE-LABEL: store_i32_stride3_vf32:
|
||||
; AVX2-FAST-PERLANE: # %bb.0:
|
||||
; AVX2-FAST-PERLANE-NEXT: subq $40, %rsp
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps (%rdi), %ymm0
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 32(%rdi), %ymm4
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 64(%rdi), %ymm8
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 32(%rsi), %ymm5
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 64(%rsi), %ymm9
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 96(%rsi), %ymm2
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 32(%rdx), %ymm10
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 64(%rdx), %ymm12
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 96(%rdx), %ymm6
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} xmm1 = mem[1,0,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm3 = ymm0[0,0,2,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm1 = ymm3[0],ymm1[1],ymm3[2,3],ymm1[4],ymm3[5,6],ymm1[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd (%rdx), %ymm3
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1],ymm3[2],ymm1[3,4],ymm3[5],ymm1[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, (%rsp) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm3 = ymm12[2,1,3,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm7 = ymm9[1,2,3,3,5,6,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm7 = ymm7[2,2,2,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm3 = ymm7[0],ymm3[1],ymm7[2,3],ymm3[4],ymm7[5,6],ymm3[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd 88(%rdi), %ymm7
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1],ymm7[2],ymm3[3,4],ymm7[5],ymm3[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm7 = ymm10[2,1,3,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm11 = ymm5[1,2,3,3,5,6,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm11 = ymm11[2,2,2,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm7 = ymm11[0],ymm7[1],ymm11[2,3],ymm7[4],ymm11[5,6],ymm7[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd 56(%rdi), %ymm11
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm7[0,1],ymm11[2],ymm7[3,4],ymm11[5],ymm7[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm11 = ymm6[2,1,3,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm13 = ymm2[1,2,3,3,5,6,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm13 = ymm13[2,2,2,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm11 = ymm13[0],ymm11[1],ymm13[2,3],ymm11[4],ymm13[5,6],ymm11[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd 120(%rdi), %ymm13
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm11 = ymm11[0,1],ymm13[2],ymm11[3,4],ymm13[5],ymm11[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} xmm13 = mem[1,0,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm13 = ymm13[0,1,0,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm14 = ymm8[0,0,2,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm13 = ymm14[0],ymm13[1],ymm14[2,3],ymm13[4],ymm14[5,6],ymm13[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd 64(%rdx), %ymm14
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm13 = ymm13[0,1],ymm14[2],ymm13[3,4],ymm14[5],ymm13[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} xmm14 = mem[1,0,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm14 = ymm14[0,1,0,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm15 = ymm4[0,0,2,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm14 = ymm15[0],ymm14[1],ymm15[2,3],ymm14[4],ymm15[5,6],ymm14[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd 32(%rdx), %ymm15
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm14 = ymm14[0,1],ymm15[2],ymm14[3,4],ymm15[5],ymm14[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} xmm15 = mem[1,0,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm15 = ymm15[0,1,0,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps 96(%rdi), %ymm2
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm1 = ymm2[0,0,2,1]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0],ymm15[1],ymm1[2,3],ymm15[4],ymm1[5,6],ymm15[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd 96(%rdx), %ymm15
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1],ymm15[2],ymm1[3,4],ymm15[5],ymm1[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps (%rsi), %ymm15
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm3 = ymm15[1,2,3,3,5,6,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[2,2,2,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps (%rdx), %ymm0
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm7 = ymm0[2,1,3,3]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0],ymm7[1],ymm3[2,3],ymm7[4],ymm3[5,6],ymm7[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd 24(%rdi), %ymm7
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm3 = ymm3[0,1],ymm7[2],ymm3[3,4],ymm7[5],ymm3[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm7 = ymm8[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm8 = ymm12[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm7 = ymm8[0],ymm7[1],ymm8[2,3],ymm7[4],ymm8[5,6],ymm7[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm8 = ymm9[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm7 = ymm7[0,1],ymm8[2],ymm7[3,4],ymm8[5],ymm7[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm8 = ymm10[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm4 = ymm8[0],ymm4[1],ymm8[2,3],ymm4[4],ymm8[5,6],ymm4[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm5 = ymm5[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm4 = ymm4[0,1],ymm5[2],ymm4[3,4],ymm5[5],ymm4[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm5 = ymm6[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm2 = ymm5[0],ymm2[1],ymm5[2,3],ymm2[4],ymm5[5,6],ymm2[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps $240, {{[-0-9]+}}(%r{{[sb]}}p), %ymm5 # 32-byte Folded Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: # ymm5 = mem[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm5[2],ymm2[3,4],ymm5[5],ymm2[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd $165, {{[-0-9]+}}(%r{{[sb]}}p), %ymm5 # 32-byte Folded Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: # ymm5 = mem[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm5[1],ymm0[2,3],ymm5[4],ymm0[5,6],ymm5[7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vpermilps {{.*#+}} ymm5 = ymm15[0,0,3,3,4,4,7,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm5[2],ymm0[3,4],ymm5[5],ymm0[6,7]
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm0, 32(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm2, 320(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm4, 128(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm7, 224(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm3, 64(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm1, 288(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm14, 96(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm13, 192(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm11, 352(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm0, 160(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm0, 256(%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovups (%rsp), %ymm0 # 32-byte Reload
|
||||
; AVX2-FAST-PERLANE-NEXT: vmovaps %ymm0, (%rcx)
|
||||
; AVX2-FAST-PERLANE-NEXT: addq $40, %rsp
|
||||
; AVX2-FAST-PERLANE-NEXT: vzeroupper
|
||||
; AVX2-FAST-PERLANE-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: store_i32_stride3_vf32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 (%rsi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 64(%rsi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 (%rdx), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdx), %zmm5
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm6 = <0,16,u,1,17,u,2,18,u,3,19,u,4,20,u,5>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm7
|
||||
; AVX512-NEXT: vpermt2d %zmm2, %zmm6, %zmm7
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm8 = [0,1,16,3,4,17,6,7,18,9,10,19,12,13,20,15]
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm8, %zmm7
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm9 = <10,27,u,11,28,u,12,29,u,13,30,u,14,31,u,15>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm10
|
||||
; AVX512-NEXT: vpermt2d %zmm1, %zmm9, %zmm10
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm11 = [0,1,27,3,4,28,6,7,29,9,10,30,12,13,31,15]
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm11, %zmm10
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm12 = <5,21,u,6,22,u,7,23,u,8,24,u,9,25,u,10>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm3, %zmm13
|
||||
; AVX512-NEXT: vpermt2d %zmm5, %zmm12, %zmm13
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm14 = [0,1,22,3,4,23,6,7,24,9,10,25,12,13,26,15]
|
||||
; AVX512-NEXT: vpermt2d %zmm1, %zmm14, %zmm13
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm6, %zmm1
|
||||
; AVX512-NEXT: vpermt2d %zmm5, %zmm8, %zmm1
|
||||
; AVX512-NEXT: vpermi2d %zmm0, %zmm4, %zmm9
|
||||
; AVX512-NEXT: vpermt2d %zmm2, %zmm11, %zmm9
|
||||
; AVX512-NEXT: vpermt2d %zmm4, %zmm12, %zmm2
|
||||
; AVX512-NEXT: vpermt2d %zmm0, %zmm14, %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 %zmm2, 64(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm9, 128(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm1, 192(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm13, 256(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm10, 320(%rcx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm7, (%rcx)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%in.vec0 = load <32 x i32>, <32 x i32>* %in.vecptr0, align 32
|
||||
%in.vec1 = load <32 x i32>, <32 x i32>* %in.vecptr1, align 32
|
||||
%in.vec2 = load <32 x i32>, <32 x i32>* %in.vecptr2, align 32
|
||||
|
||||
%concat01 = shufflevector <32 x i32> %in.vec0, <32 x i32> %in.vec1, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
|
||||
%concat2u = shufflevector <32 x i32> %in.vec2, <32 x i32> poison, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
||||
%concat012 = shufflevector <64 x i32> %concat01, <64 x i32> %concat2u, <96 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, i32 64, i32 65, i32 66, i32 67, i32 68, i32 69, i32 70, i32 71, i32 72, i32 73, i32 74, i32 75, i32 76, i32 77, i32 78, i32 79, i32 80, i32 81, i32 82, i32 83, i32 84, i32 85, i32 86, i32 87, i32 88, i32 89, i32 90, i32 91, i32 92, i32 93, i32 94, i32 95>
|
||||
%interleaved.vec = shufflevector <96 x i32> %concat012, <96 x i32> poison, <96 x i32> <i32 0, i32 32, i32 64, i32 1, i32 33, i32 65, i32 2, i32 34, i32 66, i32 3, i32 35, i32 67, i32 4, i32 36, i32 68, i32 5, i32 37, i32 69, i32 6, i32 38, i32 70, i32 7, i32 39, i32 71, i32 8, i32 40, i32 72, i32 9, i32 41, i32 73, i32 10, i32 42, i32 74, i32 11, i32 43, i32 75, i32 12, i32 44, i32 76, i32 13, i32 45, i32 77, i32 14, i32 46, i32 78, i32 15, i32 47, i32 79, i32 16, i32 48, i32 80, i32 17, i32 49, i32 81, i32 18, i32 50, i32 82, i32 19, i32 51, i32 83, i32 20, i32 52, i32 84, i32 21, i32 53, i32 85, i32 22, i32 54, i32 86, i32 23, i32 55, i32 87, i32 24, i32 56, i32 88, i32 25, i32 57, i32 89, i32 26, i32 58, i32 90, i32 27, i32 59, i32 91, i32 28, i32 60, i32 92, i32 29, i32 61, i32 93, i32 30, i32 62, i32 94, i32 31, i32 63, i32 95>
|
||||
|
||||
store <96 x i32> %interleaved.vec, <96 x i32>* %out.vec, align 32
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
|
|
@ -690,3 +690,678 @@ define void @store_i32_stride4_vf16(<16 x i32>* %in.vecptr0, <16 x i32>* %in.vec
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @store_i32_stride4_vf32(<32 x i32>* %in.vecptr0, <32 x i32>* %in.vecptr1, <32 x i32>* %in.vecptr2, <32 x i32>* %in.vecptr3, <128 x i32>* %out.vec) nounwind {
|
||||
; SSE-LABEL: store_i32_stride4_vf32:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $184, %rsp
|
||||
; SSE-NEXT: movaps (%rdi), %xmm14
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm11
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm13
|
||||
; SSE-NEXT: movaps (%rsi), %xmm15
|
||||
; SSE-NEXT: movaps 16(%rsi), %xmm9
|
||||
; SSE-NEXT: movaps 32(%rsi), %xmm8
|
||||
; SSE-NEXT: movaps (%rdx), %xmm2
|
||||
; SSE-NEXT: movaps 16(%rdx), %xmm4
|
||||
; SSE-NEXT: movaps 32(%rdx), %xmm1
|
||||
; SSE-NEXT: movaps (%rcx), %xmm7
|
||||
; SSE-NEXT: movaps 16(%rcx), %xmm0
|
||||
; SSE-NEXT: movaps 32(%rcx), %xmm10
|
||||
; SSE-NEXT: movaps %xmm2, %xmm6
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1]
|
||||
; SSE-NEXT: movaps %xmm14, %xmm5
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm5 = xmm5[0],xmm15[0],xmm5[1],xmm15[1]
|
||||
; SSE-NEXT: movaps %xmm5, %xmm3
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm3 = xmm3[0],xmm6[0]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm6[1]
|
||||
; SSE-NEXT: movaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm2 = xmm2[2],xmm7[2],xmm2[3],xmm7[3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm14 = xmm14[2],xmm15[2],xmm14[3],xmm15[3]
|
||||
; SSE-NEXT: movaps %xmm14, %xmm5
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm5 = xmm5[0],xmm2[0]
|
||||
; SSE-NEXT: movaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm4, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm11, %xmm3
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1]
|
||||
; SSE-NEXT: movaps %xmm3, %xmm5
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm5 = xmm5[0],xmm2[0]
|
||||
; SSE-NEXT: movaps %xmm5, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm4 = xmm4[2],xmm0[2],xmm4[3],xmm0[3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm11 = xmm11[2],xmm9[2],xmm11[3],xmm9[3]
|
||||
; SSE-NEXT: movaps %xmm11, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm4[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm11 = xmm11[1],xmm4[1]
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm1, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm2
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm8[0],xmm2[1],xmm8[1]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm3
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 48(%rdx), %xmm0
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm1 = xmm1[2],xmm10[2],xmm1[3],xmm10[3]
|
||||
; SSE-NEXT: movaps 48(%rcx), %xmm2
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm12 = xmm12[2],xmm8[2],xmm12[3],xmm8[3]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm3
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm3 = xmm3[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm3, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm0, %xmm1
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
||||
; SSE-NEXT: movaps 48(%rsi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm13, %xmm15
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm15 = xmm15[0],xmm3[0],xmm15[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm15, %xmm4
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm4 = xmm4[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm4, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm15 = xmm15[1],xmm1[1]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm0 = xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm13 = xmm13[2],xmm3[2],xmm13[3],xmm3[3]
|
||||
; SSE-NEXT: movaps %xmm13, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm13 = xmm13[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 64(%rdx), %xmm0
|
||||
; SSE-NEXT: movaps 64(%rcx), %xmm2
|
||||
; SSE-NEXT: movaps %xmm0, %xmm3
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps 64(%rsi), %xmm4
|
||||
; SSE-NEXT: movaps %xmm10, %xmm12
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm12 = xmm12[0],xmm4[0],xmm12[1],xmm4[1]
|
||||
; SSE-NEXT: movaps %xmm12, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm3[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm3[1]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm0 = xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm10 = xmm10[2],xmm4[2],xmm10[3],xmm4[3]
|
||||
; SSE-NEXT: movaps %xmm10, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 80(%rdx), %xmm0
|
||||
; SSE-NEXT: movaps 80(%rcx), %xmm3
|
||||
; SSE-NEXT: movaps %xmm0, %xmm4
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm5
|
||||
; SSE-NEXT: movaps 80(%rsi), %xmm6
|
||||
; SSE-NEXT: movaps %xmm5, %xmm14
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm14 = xmm14[0],xmm6[0],xmm14[1],xmm6[1]
|
||||
; SSE-NEXT: movaps %xmm14, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm4[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm4[1]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm0 = xmm0[2],xmm3[2],xmm0[3],xmm3[3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm5 = xmm5[2],xmm6[2],xmm5[3],xmm6[3]
|
||||
; SSE-NEXT: movaps %xmm5, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 96(%rdx), %xmm1
|
||||
; SSE-NEXT: movaps 96(%rcx), %xmm6
|
||||
; SSE-NEXT: movaps %xmm1, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1]
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 96(%rsi), %xmm7
|
||||
; SSE-NEXT: movaps %xmm3, %xmm4
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1]
|
||||
; SSE-NEXT: movaps %xmm4, %xmm13
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm13 = xmm13[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm0[1]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm1 = xmm1[2],xmm6[2],xmm1[3],xmm6[3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm3 = xmm3[2],xmm7[2],xmm3[3],xmm7[3]
|
||||
; SSE-NEXT: movaps %xmm3, %xmm11
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm11 = xmm11[0],xmm1[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 112(%rdx), %xmm2
|
||||
; SSE-NEXT: movaps 112(%rcx), %xmm9
|
||||
; SSE-NEXT: movaps %xmm2, %xmm7
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm7 = xmm7[0],xmm9[0],xmm7[1],xmm9[1]
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 112(%rsi), %xmm8
|
||||
; SSE-NEXT: movaps %xmm0, %xmm1
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm8[0],xmm1[1],xmm8[1]
|
||||
; SSE-NEXT: movaps %xmm1, %xmm6
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm6 = xmm6[0],xmm7[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm7[1]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm2 = xmm2[2],xmm9[2],xmm2[3],xmm9[3]
|
||||
; SSE-NEXT: unpckhps {{.*#+}} xmm0 = xmm0[2],xmm8[2],xmm0[3],xmm8[3]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm7
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm7 = xmm7[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm0, 496(%r8)
|
||||
; SSE-NEXT: movaps %xmm7, 480(%r8)
|
||||
; SSE-NEXT: movaps %xmm1, 464(%r8)
|
||||
; SSE-NEXT: movaps %xmm6, 448(%r8)
|
||||
; SSE-NEXT: movaps %xmm3, 432(%r8)
|
||||
; SSE-NEXT: movaps %xmm11, 416(%r8)
|
||||
; SSE-NEXT: movaps %xmm4, 400(%r8)
|
||||
; SSE-NEXT: movaps %xmm13, 384(%r8)
|
||||
; SSE-NEXT: movaps %xmm5, 368(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 352(%r8)
|
||||
; SSE-NEXT: movaps %xmm14, 336(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 320(%r8)
|
||||
; SSE-NEXT: movaps %xmm10, 304(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 288(%r8)
|
||||
; SSE-NEXT: movaps %xmm12, 272(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 256(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 240(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 224(%r8)
|
||||
; SSE-NEXT: movaps %xmm15, 208(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 192(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 176(%r8)
|
||||
; SSE-NEXT: movaps (%rsp), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 160(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 144(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 128(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, (%r8)
|
||||
; SSE-NEXT: addq $184, %rsp
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: store_i32_stride4_vf32:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: subq $456, %rsp # imm = 0x1C8
|
||||
; AVX1-NEXT: vmovaps 16(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 16(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps 16(%rcx), %xmm3
|
||||
; AVX1-NEXT: vmovaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 16(%rdx), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm2 = xmm3[0],xmm2[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[0,1,2,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 64(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps 64(%rcx), %xmm3
|
||||
; AVX1-NEXT: vmovaps %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 64(%rdx), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm2 = xmm3[0],xmm2[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[0,1,2,0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 80(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 80(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps 80(%rcx), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 80(%rdx), %xmm7
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm2[0],xmm7[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,1,2,0]
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm2 = xmm7[0],xmm2[0],xmm7[1],xmm2[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 32(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps 32(%rcx), %xmm13
|
||||
; AVX1-NEXT: vmovaps 32(%rdx), %xmm10
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm13[0],xmm10[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,1,2,0]
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm2 = xmm10[0],xmm13[0],xmm10[1],xmm13[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 48(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 48(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps 48(%rcx), %xmm11
|
||||
; AVX1-NEXT: vmovaps 48(%rdx), %xmm9
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm11[0],xmm9[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,1,2,0]
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm2 = xmm9[0],xmm11[0],xmm9[1],xmm11[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 96(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, (%rsp) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps 96(%rcx), %xmm12
|
||||
; AVX1-NEXT: vmovaps 96(%rdx), %xmm5
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm12[0],xmm5[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,1,2,0]
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm2 = xmm5[0],xmm12[0],xmm5[1],xmm12[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 112(%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 112(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps 112(%rcx), %xmm4
|
||||
; AVX1-NEXT: vmovaps 112(%rdx), %xmm3
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm4[0],xmm3[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,1,2,0]
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm6 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps (%rdi), %xmm2
|
||||
; AVX1-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps (%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[1],xmm1[1],zero,zero
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vmovaps (%rcx), %xmm8
|
||||
; AVX1-NEXT: vmovaps (%rdx), %xmm2
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm15 = xmm8[0],xmm2[0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm15 = xmm15[0,1,2,0]
|
||||
; AVX1-NEXT: vunpcklps {{.*#+}} xmm14 = xmm2[0],xmm8[0],xmm2[1],xmm8[1]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm14, %ymm15, %ymm14
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm15 = ymm0[0,1],ymm14[2,3],ymm0[4,5],ymm14[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm0 = xmm1[2],xmm6[2],xmm1[3],xmm6[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm14 = zero,zero,xmm1[2],xmm6[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm14, %ymm1
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm14 = xmm0[2],xmm6[2],xmm0[3],xmm6[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm6 = xmm6[3,0],xmm0[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm14, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1],ymm1[2,3],ymm6[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm0 = xmm7[2],xmm1[2],xmm7[3],xmm1[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm6 = zero,zero,xmm7[2],xmm1[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm6, %ymm0
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm6 = xmm7[2],xmm1[2],xmm7[3],xmm1[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm1[3,0],xmm7[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm14 = ymm6[0,1],ymm0[2,3],ymm6[4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm6 = xmm10[2],xmm13[2],xmm10[3],xmm13[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm7 = zero,zero,xmm10[2],xmm13[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm7, %ymm6
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm7 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm1[3,0],xmm0[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm7, %ymm0
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm10 = ymm0[0,1],ymm6[2,3],ymm0[4,5],ymm6[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm0 = xmm9[2],xmm11[2],xmm9[3],xmm11[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm6 = zero,zero,xmm9[2],xmm11[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm6, %ymm0
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm6 = xmm1[2],xmm7[2],xmm1[3],xmm7[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm7 = xmm7[3,0],xmm1[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm7 = xmm7[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm6, %ymm6
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm9 = ymm6[0,1],ymm0[2,3],ymm6[4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm0 = xmm5[2],xmm12[2],xmm5[3],xmm12[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm5 = zero,zero,xmm5[2],xmm12[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm5, %ymm0
|
||||
; AVX1-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm5 = xmm6[2],xmm1[2],xmm6[3],xmm1[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm6 = xmm1[3,0],xmm6[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm6 = xmm6[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm5, %ymm5
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1],ymm0[2,3],ymm5[4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm0 = xmm3[2],xmm4[2],xmm3[3],xmm4[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm3 = zero,zero,xmm3[2],xmm4[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm3, %ymm0
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm3 = xmm4[2],xmm1[2],xmm4[3],xmm1[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm4 = xmm1[3,0],xmm4[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1],ymm0[2,3],ymm3[4,5],ymm0[6,7]
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm3 = xmm2[2],xmm8[2],xmm2[3],xmm8[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm1 = zero,zero,xmm2[2],xmm8[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm1, %ymm1
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm2 = xmm3[2],xmm4[2],xmm3[3],xmm4[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm3 = xmm4[3,0],xmm3[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm2
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1],ymm1[2,3],ymm2[4,5],ymm1[6,7]
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm3 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm2 = xmm3[2],xmm4[2],xmm3[3],xmm4[3]
|
||||
; AVX1-NEXT: vinsertps {{.*#+}} xmm3 = zero,zero,xmm3[2],xmm4[2]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm4 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm6 # 16-byte Reload
|
||||
; AVX1-NEXT: vunpckhps {{.*#+}} xmm3 = xmm6[2],xmm4[2],xmm6[3],xmm4[3]
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm4 = xmm4[3,0],xmm6[3,0]
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[2,0,2,3]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
|
||||
; AVX1-NEXT: vmovaps %ymm2, 96(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm1, 32(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm0, 480(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm5, 416(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm9, 224(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm10, 160(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm14, 352(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 288(%r8)
|
||||
; AVX1-NEXT: vmovaps %ymm15, (%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 448(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 384(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 192(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 128(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 320(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 256(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 64(%r8)
|
||||
; AVX1-NEXT: addq $456, %rsp # imm = 0x1C8
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: store_i32_stride4_vf32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: subq $168, %rsp
|
||||
; AVX2-NEXT: vmovaps (%rdi), %ymm0
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps (%rsi), %ymm0
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 64(%rdx), %ymm6
|
||||
; AVX2-NEXT: vmovaps (%rdx), %ymm2
|
||||
; AVX2-NEXT: vmovaps (%rcx), %xmm13
|
||||
; AVX2-NEXT: vmovaps 32(%rcx), %xmm10
|
||||
; AVX2-NEXT: vmovaps 64(%rcx), %xmm11
|
||||
; AVX2-NEXT: vmovaps (%rdx), %xmm14
|
||||
; AVX2-NEXT: vmovaps 32(%rdx), %xmm12
|
||||
; AVX2-NEXT: vmovaps 64(%rdx), %xmm3
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm8 = xmm3[2],xmm11[2],xmm3[3],xmm11[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm8 = ymm8[0,0,2,1]
|
||||
; AVX2-NEXT: vmovaps 32(%rsi), %xmm4
|
||||
; AVX2-NEXT: vmovaps 64(%rsi), %xmm7
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %xmm0
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %xmm5
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm9 = xmm5[2],xmm7[2],xmm5[3],xmm7[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm9 = ymm9[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm9[0,1],ymm8[2,3],ymm9[4,5],ymm8[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm3 = xmm3[0],xmm11[0],xmm3[1],xmm11[1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[0,0,2,1]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm5 = xmm5[0],xmm7[0],xmm5[1],xmm7[1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm5 = ymm5[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm5[0,1],ymm3[2,3],ymm5[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm3 = xmm12[2],xmm10[2],xmm12[3],xmm10[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[0,0,2,1]
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm5 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm5 = ymm5[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm5[0,1],ymm3[2,3],ymm5[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm3 = xmm12[0],xmm10[0],xmm12[1],xmm10[1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[0,0,2,1]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm3[2,3],ymm0[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, (%rsp) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 96(%rcx), %xmm10
|
||||
; AVX2-NEXT: vmovaps 96(%rdx), %xmm3
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm4 = xmm3[2],xmm10[2],xmm3[3],xmm10[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm8 = ymm4[0,0,2,1]
|
||||
; AVX2-NEXT: vmovaps 96(%rsi), %xmm4
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %xmm0
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm12 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm12 = ymm12[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm12[0,1],ymm8[2,3],ymm12[4,5],ymm8[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps (%rsi), %xmm1
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm3 = xmm3[0],xmm10[0],xmm3[1],xmm10[1]
|
||||
; AVX2-NEXT: vmovaps (%rdi), %xmm10
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[0,0,2,1]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm3[2,3],ymm0[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm3 = xmm14[2],xmm13[2],xmm14[3],xmm13[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[0,0,2,1]
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} xmm4 = xmm10[2],xmm1[2],xmm10[3],xmm1[3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm4[0,1],ymm3[2,3],ymm4[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 64(%rcx), %ymm0
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm3 = xmm14[0],xmm13[0],xmm14[1],xmm13[1]
|
||||
; AVX2-NEXT: vmovaps (%rcx), %ymm13
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[0,0,2,1]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} xmm1 = xmm10[0],xmm1[0],xmm10[1],xmm1[1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm15 = ymm1[0,1],ymm3[2,3],ymm1[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovaps %ymm2, %ymm5
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm1 = ymm2[0],ymm13[0],ymm2[1],ymm13[1],ymm2[4],ymm13[4],ymm2[5],ymm13[5]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm3 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm4 = ymm3[0],ymm2[0],ymm3[1],ymm2[1],ymm3[4],ymm2[4],ymm3[5],ymm2[5]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm12 = ymm4[0,1],ymm1[2,3],ymm4[4,5],ymm1[6,7]
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm1 = ymm6[2],ymm0[2],ymm6[3],ymm0[3],ymm6[6],ymm0[6],ymm6[7],ymm0[7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %ymm10
|
||||
; AVX2-NEXT: vmovaps 64(%rsi), %ymm14
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm9 = ymm10[2],ymm14[2],ymm10[3],ymm14[3],ymm10[6],ymm14[6],ymm10[7],ymm14[7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm9 = ymm9[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm7 = ymm9[0,1],ymm1[2,3],ymm9[4,5],ymm1[6,7]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm0 = ymm6[0],ymm0[0],ymm6[1],ymm0[1],ymm6[4],ymm0[4],ymm6[5],ymm0[5]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm6 = ymm10[0],ymm14[0],ymm10[1],ymm14[1],ymm10[4],ymm14[4],ymm10[5],ymm14[5]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm6 = ymm6[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm4 = ymm6[0,1],ymm0[2,3],ymm6[4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vmovaps 32(%rdx), %ymm6
|
||||
; AVX2-NEXT: vmovaps 32(%rcx), %ymm9
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm10 = ymm6[2],ymm9[2],ymm6[3],ymm9[3],ymm6[6],ymm9[6],ymm6[7],ymm9[7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm10 = ymm10[0,2,2,3]
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %ymm14
|
||||
; AVX2-NEXT: vmovaps 32(%rsi), %ymm0
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm11 = ymm14[2],ymm0[2],ymm14[3],ymm0[3],ymm14[6],ymm0[6],ymm14[7],ymm0[7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm11 = ymm11[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm10 = ymm11[0,1],ymm10[2,3],ymm11[4,5],ymm10[6,7]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm6 = ymm6[0],ymm9[0],ymm6[1],ymm9[1],ymm6[4],ymm9[4],ymm6[5],ymm9[5]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm0 = ymm14[0],ymm0[0],ymm14[1],ymm0[1],ymm14[4],ymm0[4],ymm14[5],ymm0[5]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm6 = ymm6[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm0[0,1],ymm6[2,3],ymm0[4,5],ymm6[6,7]
|
||||
; AVX2-NEXT: vmovaps 96(%rdx), %ymm6
|
||||
; AVX2-NEXT: vmovaps 96(%rcx), %ymm9
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm11 = ymm6[2],ymm9[2],ymm6[3],ymm9[3],ymm6[6],ymm9[6],ymm6[7],ymm9[7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm11 = ymm11[0,2,2,3]
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %ymm14
|
||||
; AVX2-NEXT: vmovaps 96(%rsi), %ymm0
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm8 = ymm14[2],ymm0[2],ymm14[3],ymm0[3],ymm14[6],ymm0[6],ymm14[7],ymm0[7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm8 = ymm8[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm8 = ymm8[0,1],ymm11[2,3],ymm8[4,5],ymm11[6,7]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm6 = ymm6[0],ymm9[0],ymm6[1],ymm9[1],ymm6[4],ymm9[4],ymm6[5],ymm9[5]
|
||||
; AVX2-NEXT: vunpcklps {{.*#+}} ymm0 = ymm14[0],ymm0[0],ymm14[1],ymm0[1],ymm14[4],ymm0[4],ymm14[5],ymm0[5]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm6 = ymm6[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm6[2,3],ymm0[4,5],ymm6[6,7]
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm6 = ymm5[2],ymm13[2],ymm5[3],ymm13[3],ymm5[6],ymm13[6],ymm5[7],ymm13[7]
|
||||
; AVX2-NEXT: vunpckhps {{.*#+}} ymm9 = ymm3[2],ymm2[2],ymm3[3],ymm2[3],ymm3[6],ymm2[6],ymm3[7],ymm2[7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm6 = ymm6[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm9 = ymm9[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm6 = ymm9[0,1],ymm6[2,3],ymm9[4,5],ymm6[6,7]
|
||||
; AVX2-NEXT: vmovaps %ymm6, 96(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm0, 448(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm8, 480(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm1, 192(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm10, 224(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm4, 320(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm7, 352(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm12, 64(%r8)
|
||||
; AVX2-NEXT: vmovaps %ymm15, (%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 32(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 384(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 416(%r8)
|
||||
; AVX2-NEXT: vmovups (%rsp), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 128(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 160(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 256(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 288(%r8)
|
||||
; AVX2-NEXT: addq $168, %rsp
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: store_i32_stride4_vf32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 (%rsi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 64(%rsi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 (%rdx), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdx), %zmm5
|
||||
; AVX512-NEXT: vmovdqu64 (%rcx), %zmm6
|
||||
; AVX512-NEXT: vmovdqu64 64(%rcx), %zmm7
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm8 = <u,u,4,20,u,u,5,21,u,u,6,22,u,u,7,23>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm9
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm8, %zmm9
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm10 = <4,20,u,u,5,21,u,u,6,22,u,u,7,23,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm11
|
||||
; AVX512-NEXT: vpermt2d %zmm2, %zmm10, %zmm11
|
||||
; AVX512-NEXT: movb $-86, %al
|
||||
; AVX512-NEXT: kmovd %eax, %k1
|
||||
; AVX512-NEXT: vmovdqa64 %zmm9, %zmm11 {%k1}
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm9 = <u,u,0,16,u,u,1,17,u,u,2,18,u,u,3,19>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm12
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm9, %zmm12
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm13 = <0,16,u,u,1,17,u,u,2,18,u,u,3,19,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm14
|
||||
; AVX512-NEXT: vpermt2d %zmm2, %zmm13, %zmm14
|
||||
; AVX512-NEXT: vmovdqa64 %zmm12, %zmm14 {%k1}
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm12 = <u,u,12,28,u,u,13,29,u,u,14,30,u,u,15,31>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm15
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm12, %zmm15
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm16 = <12,28,u,u,13,29,u,u,14,30,u,u,15,31,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm17
|
||||
; AVX512-NEXT: vpermt2d %zmm2, %zmm16, %zmm17
|
||||
; AVX512-NEXT: vmovdqa64 %zmm15, %zmm17 {%k1}
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm15 = <u,u,8,24,u,u,9,25,u,u,10,26,u,u,11,27>
|
||||
; AVX512-NEXT: vpermt2d %zmm6, %zmm15, %zmm4
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm6 = <8,24,u,u,9,25,u,u,10,26,u,u,11,27,u,u>
|
||||
; AVX512-NEXT: vpermt2d %zmm2, %zmm6, %zmm0
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm0 {%k1}
|
||||
; AVX512-NEXT: vpermi2d %zmm7, %zmm5, %zmm8
|
||||
; AVX512-NEXT: vpermi2d %zmm3, %zmm1, %zmm10
|
||||
; AVX512-NEXT: vmovdqa64 %zmm8, %zmm10 {%k1}
|
||||
; AVX512-NEXT: vpermi2d %zmm7, %zmm5, %zmm9
|
||||
; AVX512-NEXT: vpermi2d %zmm3, %zmm1, %zmm13
|
||||
; AVX512-NEXT: vmovdqa64 %zmm9, %zmm13 {%k1}
|
||||
; AVX512-NEXT: vpermi2d %zmm7, %zmm5, %zmm12
|
||||
; AVX512-NEXT: vpermi2d %zmm3, %zmm1, %zmm16
|
||||
; AVX512-NEXT: vmovdqa64 %zmm12, %zmm16 {%k1}
|
||||
; AVX512-NEXT: vpermt2d %zmm7, %zmm15, %zmm5
|
||||
; AVX512-NEXT: vpermt2d %zmm3, %zmm6, %zmm1
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm1 {%k1}
|
||||
; AVX512-NEXT: vmovdqu64 %zmm1, 384(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm16, 448(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm13, 256(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm10, 320(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm0, 128(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm17, 192(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm14, (%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm11, 64(%r8)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%in.vec0 = load <32 x i32>, <32 x i32>* %in.vecptr0, align 32
|
||||
%in.vec1 = load <32 x i32>, <32 x i32>* %in.vecptr1, align 32
|
||||
%in.vec2 = load <32 x i32>, <32 x i32>* %in.vecptr2, align 32
|
||||
%in.vec3 = load <32 x i32>, <32 x i32>* %in.vecptr3, align 32
|
||||
|
||||
%concat01 = shufflevector <32 x i32> %in.vec0, <32 x i32> %in.vec1, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
|
||||
%concat23 = shufflevector <32 x i32> %in.vec2, <32 x i32> %in.vec3, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
|
||||
%concat0123 = shufflevector <64 x i32> %concat01, <64 x i32> %concat23, <128 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, i32 64, i32 65, i32 66, i32 67, i32 68, i32 69, i32 70, i32 71, i32 72, i32 73, i32 74, i32 75, i32 76, i32 77, i32 78, i32 79, i32 80, i32 81, i32 82, i32 83, i32 84, i32 85, i32 86, i32 87, i32 88, i32 89, i32 90, i32 91, i32 92, i32 93, i32 94, i32 95, i32 96, i32 97, i32 98, i32 99, i32 100, i32 101, i32 102, i32 103, i32 104, i32 105, i32 106, i32 107, i32 108, i32 109, i32 110, i32 111, i32 112, i32 113, i32 114, i32 115, i32 116, i32 117, i32 118, i32 119, i32 120, i32 121, i32 122, i32 123, i32 124, i32 125, i32 126, i32 127>
|
||||
%interleaved.vec = shufflevector <128 x i32> %concat0123, <128 x i32> poison, <128 x i32> <i32 0, i32 32, i32 64, i32 96, i32 1, i32 33, i32 65, i32 97, i32 2, i32 34, i32 66, i32 98, i32 3, i32 35, i32 67, i32 99, i32 4, i32 36, i32 68, i32 100, i32 5, i32 37, i32 69, i32 101, i32 6, i32 38, i32 70, i32 102, i32 7, i32 39, i32 71, i32 103, i32 8, i32 40, i32 72, i32 104, i32 9, i32 41, i32 73, i32 105, i32 10, i32 42, i32 74, i32 106, i32 11, i32 43, i32 75, i32 107, i32 12, i32 44, i32 76, i32 108, i32 13, i32 45, i32 77, i32 109, i32 14, i32 46, i32 78, i32 110, i32 15, i32 47, i32 79, i32 111, i32 16, i32 48, i32 80, i32 112, i32 17, i32 49, i32 81, i32 113, i32 18, i32 50, i32 82, i32 114, i32 19, i32 51, i32 83, i32 115, i32 20, i32 52, i32 84, i32 116, i32 21, i32 53, i32 85, i32 117, i32 22, i32 54, i32 86, i32 118, i32 23, i32 55, i32 87, i32 119, i32 24, i32 56, i32 88, i32 120, i32 25, i32 57, i32 89, i32 121, i32 26, i32 58, i32 90, i32 122, i32 27, i32 59, i32 91, i32 123, i32 28, i32 60, i32 92, i32 124, i32 29, i32 61, i32 93, i32 125, i32 30, i32 62, i32 94, i32 126, i32 31, i32 63, i32 95, i32 127>
|
||||
|
||||
store <128 x i32> %interleaved.vec, <128 x i32>* %out.vec, align 32
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
|
|
@ -416,3 +416,375 @@ define void @store_i64_stride2_vf16(<16 x i64>* %in.vecptr0, <16 x i64>* %in.vec
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @store_i64_stride2_vf32(<32 x i64>* %in.vecptr0, <32 x i64>* %in.vecptr1, <64 x i64>* %out.vec) nounwind {
|
||||
; SSE-LABEL: store_i64_stride2_vf32:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $152, %rsp
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm14
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm13
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm11
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps (%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm8
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps 96(%rsi), %xmm15
|
||||
; SSE-NEXT: movaps 80(%rsi), %xmm1
|
||||
; SSE-NEXT: movaps 64(%rsi), %xmm2
|
||||
; SSE-NEXT: movaps (%rsi), %xmm3
|
||||
; SSE-NEXT: movaps 16(%rsi), %xmm4
|
||||
; SSE-NEXT: movaps 32(%rsi), %xmm5
|
||||
; SSE-NEXT: movaps 48(%rsi), %xmm6
|
||||
; SSE-NEXT: movaps %xmm0, %xmm7
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm7 = xmm7[0],xmm3[0]
|
||||
; SSE-NEXT: movaps %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm8, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm4[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm8 = xmm8[1],xmm4[1]
|
||||
; SSE-NEXT: movaps %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm9, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm5[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm9 = xmm9[1],xmm5[1]
|
||||
; SSE-NEXT: movaps %xmm9, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm12, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm6[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm6[1]
|
||||
; SSE-NEXT: movaps %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm10, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm11, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm11 = xmm11[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm11, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm13, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm15[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm13 = xmm13[1],xmm15[1]
|
||||
; SSE-NEXT: movaps %xmm13, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 112(%rsi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm14, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 128(%rdi), %xmm14
|
||||
; SSE-NEXT: movaps 128(%rsi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm14, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 144(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps 144(%rsi), %xmm2
|
||||
; SSE-NEXT: movaps %xmm10, %xmm15
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm15 = xmm15[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm2[1]
|
||||
; SSE-NEXT: movaps 160(%rdi), %xmm12
|
||||
; SSE-NEXT: movaps 160(%rsi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm12, %xmm13
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm13 = xmm13[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 176(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 176(%rsi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm9, %xmm11
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm11 = xmm11[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm9 = xmm9[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 192(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps 192(%rsi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm7, %xmm8
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm8 = xmm8[0],xmm1[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm7 = xmm7[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 208(%rdi), %xmm1
|
||||
; SSE-NEXT: movaps 208(%rsi), %xmm2
|
||||
; SSE-NEXT: movaps %xmm1, %xmm6
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm6 = xmm6[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm2[1]
|
||||
; SSE-NEXT: movaps 224(%rdi), %xmm2
|
||||
; SSE-NEXT: movaps 224(%rsi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm2, %xmm4
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm4 = xmm4[0],xmm3[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm3[1]
|
||||
; SSE-NEXT: movaps 240(%rdi), %xmm3
|
||||
; SSE-NEXT: movaps 240(%rsi), %xmm5
|
||||
; SSE-NEXT: movaps %xmm3, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm5[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm5[1]
|
||||
; SSE-NEXT: movaps %xmm3, 496(%rdx)
|
||||
; SSE-NEXT: movaps %xmm0, 480(%rdx)
|
||||
; SSE-NEXT: movaps %xmm2, 464(%rdx)
|
||||
; SSE-NEXT: movaps %xmm4, 448(%rdx)
|
||||
; SSE-NEXT: movaps %xmm1, 432(%rdx)
|
||||
; SSE-NEXT: movaps %xmm6, 416(%rdx)
|
||||
; SSE-NEXT: movaps %xmm7, 400(%rdx)
|
||||
; SSE-NEXT: movaps %xmm8, 384(%rdx)
|
||||
; SSE-NEXT: movaps %xmm9, 368(%rdx)
|
||||
; SSE-NEXT: movaps %xmm11, 352(%rdx)
|
||||
; SSE-NEXT: movaps %xmm12, 336(%rdx)
|
||||
; SSE-NEXT: movaps %xmm13, 320(%rdx)
|
||||
; SSE-NEXT: movaps %xmm10, 304(%rdx)
|
||||
; SSE-NEXT: movaps %xmm15, 288(%rdx)
|
||||
; SSE-NEXT: movaps %xmm14, 272(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 256(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 240(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 224(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 208(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 192(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 176(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 160(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 144(%rdx)
|
||||
; SSE-NEXT: movaps (%rsp), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 128(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%rdx)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, (%rdx)
|
||||
; SSE-NEXT: addq $152, %rsp
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: store_i64_stride2_vf32:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vmovaps 224(%rsi), %xmm0
|
||||
; AVX1-NEXT: vmovaps 224(%rdi), %xmm1
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm1[1],xmm0[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 128(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps 128(%rdi), %xmm2
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm2[0],xmm1[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm1, %ymm9
|
||||
; AVX1-NEXT: vmovaps (%rsi), %xmm2
|
||||
; AVX1-NEXT: vmovaps 32(%rsi), %xmm3
|
||||
; AVX1-NEXT: vmovaps 64(%rsi), %xmm4
|
||||
; AVX1-NEXT: vmovaps 96(%rsi), %xmm10
|
||||
; AVX1-NEXT: vmovaps (%rdi), %xmm6
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %xmm7
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %xmm0
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %xmm1
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm5 = xmm6[1],xmm2[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm2 = xmm6[0],xmm2[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm2, %ymm2
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm5 = xmm7[1],xmm3[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm3 = xmm7[0],xmm3[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm5 = xmm0[1],xmm4[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm4[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm0, %ymm4
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm1[1],xmm10[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm1[0],xmm10[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm5
|
||||
; AVX1-NEXT: vmovaps 160(%rsi), %xmm0
|
||||
; AVX1-NEXT: vmovaps 160(%rdi), %xmm1
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm6 = xmm1[1],xmm0[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm6
|
||||
; AVX1-NEXT: vmovapd 192(%rsi), %xmm0
|
||||
; AVX1-NEXT: vmovapd 192(%rdi), %xmm1
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm7 = xmm1[1],xmm0[1]
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm7
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[3],ymm0[3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm10 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm1 = ymm10[0],ymm1[0],ymm10[3],ymm1[3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm10 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm11 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm10 = ymm11[0],ymm10[0],ymm11[3],ymm10[3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm11 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm12 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm11 = ymm12[0],ymm11[0],ymm12[3],ymm11[3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm12 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm13 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm12 = ymm13[0],ymm12[0],ymm13[3],ymm12[3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm13 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm14 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm13 = ymm14[0],ymm13[0],ymm14[3],ymm13[3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm14 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm15 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm14 = ymm15[0],ymm14[0],ymm15[3],ymm14[3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm15 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm8 = mem[2,3,2,3]
|
||||
; AVX1-NEXT: vshufpd {{.*#+}} ymm8 = ymm8[0],ymm15[0],ymm8[3],ymm15[3]
|
||||
; AVX1-NEXT: vmovapd %ymm8, 480(%rdx)
|
||||
; AVX1-NEXT: vmovapd %ymm14, 416(%rdx)
|
||||
; AVX1-NEXT: vmovapd %ymm13, 352(%rdx)
|
||||
; AVX1-NEXT: vmovapd %ymm12, 224(%rdx)
|
||||
; AVX1-NEXT: vmovapd %ymm11, 160(%rdx)
|
||||
; AVX1-NEXT: vmovapd %ymm10, 96(%rdx)
|
||||
; AVX1-NEXT: vmovapd %ymm1, 32(%rdx)
|
||||
; AVX1-NEXT: vmovapd %ymm0, 288(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm7, 384(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm6, 320(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm5, 192(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm4, 128(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm3, 64(%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm2, (%rdx)
|
||||
; AVX1-NEXT: vmovaps %ymm9, 256(%rdx)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 448(%rdx)
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: store_i64_stride2_vf32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vmovaps 192(%rdi), %ymm2
|
||||
; AVX2-NEXT: vmovaps 160(%rdi), %ymm5
|
||||
; AVX2-NEXT: vmovaps 128(%rdi), %ymm8
|
||||
; AVX2-NEXT: vmovaps (%rdi), %ymm1
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %ymm4
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %ymm9
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %ymm12
|
||||
; AVX2-NEXT: vmovaps 192(%rsi), %ymm6
|
||||
; AVX2-NEXT: vmovaps 160(%rsi), %ymm10
|
||||
; AVX2-NEXT: vmovaps 128(%rsi), %ymm13
|
||||
; AVX2-NEXT: vmovaps (%rsi), %ymm3
|
||||
; AVX2-NEXT: vmovaps 32(%rsi), %ymm7
|
||||
; AVX2-NEXT: vmovaps 64(%rsi), %ymm11
|
||||
; AVX2-NEXT: vmovaps 96(%rsi), %ymm14
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm3[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm15 = ymm1[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm15[0,1],ymm0[2,3],ymm15[4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm3[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1],ymm3[2,3],ymm1[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm7[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm15 = ymm4[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm3 = ymm15[0,1],ymm3[2,3],ymm15[4,5],ymm3[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm7 = ymm7[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm4 = ymm4[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm4 = ymm4[0,1],ymm7[2,3],ymm4[4,5],ymm7[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm7 = ymm11[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm15 = ymm9[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm7 = ymm15[0,1],ymm7[2,3],ymm15[4,5],ymm7[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm11 = ymm11[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm9 = ymm9[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm9 = ymm9[0,1],ymm11[2,3],ymm9[4,5],ymm11[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm11 = ymm14[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm15 = ymm12[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm11 = ymm15[0,1],ymm11[2,3],ymm15[4,5],ymm11[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm14 = ymm14[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm12 = ymm12[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm12 = ymm12[0,1],ymm14[2,3],ymm12[4,5],ymm14[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm14 = ymm13[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm15 = ymm8[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm14 = ymm15[0,1],ymm14[2,3],ymm15[4,5],ymm14[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm13 = ymm13[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm8 = ymm8[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm8 = ymm8[0,1],ymm13[2,3],ymm8[4,5],ymm13[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm13 = ymm10[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm15 = ymm5[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm13 = ymm15[0,1],ymm13[2,3],ymm15[4,5],ymm13[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm10 = ymm10[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm5 = ymm5[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm5 = ymm5[0,1],ymm10[2,3],ymm5[4,5],ymm10[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm10 = ymm6[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm15 = ymm2[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm10 = ymm15[0,1],ymm10[2,3],ymm15[4,5],ymm10[6,7]
|
||||
; AVX2-NEXT: vmovaps 224(%rdi), %ymm15
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm6 = ymm6[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1],ymm6[2,3],ymm2[4,5],ymm6[6,7]
|
||||
; AVX2-NEXT: vmovaps 224(%rsi), %ymm6
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm6[0,2,2,3]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm15[2,1,3,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm6[0,0,2,1]
|
||||
; AVX2-NEXT: vpermpd {{.*#+}} ymm6 = ymm15[0,1,1,3]
|
||||
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm6[0,1],ymm1[2,3],ymm6[4,5],ymm1[6,7]
|
||||
; AVX2-NEXT: vmovaps %ymm1, 448(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm0, 480(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm2, 384(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm10, 416(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm5, 320(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm13, 352(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm8, 256(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm14, 288(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm12, 192(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm11, 224(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm9, 128(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm7, 160(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm4, 64(%rdx)
|
||||
; AVX2-NEXT: vmovaps %ymm3, 96(%rdx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, (%rdx)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 32(%rdx)
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: store_i64_stride2_vf32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 128(%rdi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 192(%rdi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 (%rsi), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 64(%rsi), %zmm5
|
||||
; AVX512-NEXT: vmovdqu64 128(%rsi), %zmm6
|
||||
; AVX512-NEXT: vmovdqu64 192(%rsi), %zmm7
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm8 = [4,12,5,13,6,14,7,15]
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm9
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm8, %zmm9
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm10 = [0,8,1,9,2,10,3,11]
|
||||
; AVX512-NEXT: vpermt2q %zmm4, %zmm10, %zmm0
|
||||
; AVX512-NEXT: vmovdqa64 %zmm1, %zmm4
|
||||
; AVX512-NEXT: vpermt2q %zmm5, %zmm8, %zmm4
|
||||
; AVX512-NEXT: vpermt2q %zmm5, %zmm10, %zmm1
|
||||
; AVX512-NEXT: vmovdqa64 %zmm2, %zmm5
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm8, %zmm5
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm10, %zmm2
|
||||
; AVX512-NEXT: vpermi2q %zmm7, %zmm3, %zmm8
|
||||
; AVX512-NEXT: vpermt2q %zmm7, %zmm10, %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 %zmm3, 384(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm8, 448(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm2, 256(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm5, 320(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm1, 128(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm4, 192(%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm0, (%rdx)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm9, 64(%rdx)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%in.vec0 = load <32 x i64>, <32 x i64>* %in.vecptr0, align 32
|
||||
%in.vec1 = load <32 x i64>, <32 x i64>* %in.vecptr1, align 32
|
||||
|
||||
%concat01 = shufflevector <32 x i64> %in.vec0, <32 x i64> %in.vec1, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
|
||||
%interleaved.vec = shufflevector <64 x i64> %concat01, <64 x i64> poison, <64 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
|
||||
|
||||
store <64 x i64> %interleaved.vec, <64 x i64>* %out.vec, align 32
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
|
|
@ -391,3 +391,473 @@ define void @store_i64_stride4_vf8(<8 x i64>* %in.vecptr0, <8 x i64>* %in.vecptr
|
|||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @store_i64_stride4_vf16(<16 x i64>* %in.vecptr0, <16 x i64>* %in.vecptr1, <16 x i64>* %in.vecptr2, <16 x i64>* %in.vecptr3, <64 x i64>* %out.vec) nounwind {
|
||||
; SSE-LABEL: store_i64_stride4_vf16:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: subq $152, %rsp
|
||||
; SSE-NEXT: movaps (%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 16(%rdi), %xmm8
|
||||
; SSE-NEXT: movaps 32(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 48(%rdi), %xmm10
|
||||
; SSE-NEXT: movaps (%rsi), %xmm1
|
||||
; SSE-NEXT: movaps 16(%rsi), %xmm2
|
||||
; SSE-NEXT: movaps 32(%rsi), %xmm13
|
||||
; SSE-NEXT: movaps 48(%rsi), %xmm11
|
||||
; SSE-NEXT: movaps (%rdx), %xmm6
|
||||
; SSE-NEXT: movaps 16(%rdx), %xmm12
|
||||
; SSE-NEXT: movaps 32(%rdx), %xmm14
|
||||
; SSE-NEXT: movaps 48(%rdx), %xmm15
|
||||
; SSE-NEXT: movaps (%rcx), %xmm3
|
||||
; SSE-NEXT: movaps 16(%rcx), %xmm4
|
||||
; SSE-NEXT: movaps 32(%rcx), %xmm5
|
||||
; SSE-NEXT: movaps %xmm0, %xmm7
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm7 = xmm7[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm7, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm6, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm3[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm6 = xmm6[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm8, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm8 = xmm8[1],xmm2[1]
|
||||
; SSE-NEXT: movaps %xmm8, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm12, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm4[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm12 = xmm12[1],xmm4[1]
|
||||
; SSE-NEXT: movaps %xmm12, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm9, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm13[0]
|
||||
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm9 = xmm9[1],xmm13[1]
|
||||
; SSE-NEXT: movaps %xmm9, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm14, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm5[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm14 = xmm14[1],xmm5[1]
|
||||
; SSE-NEXT: movaps %xmm14, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps %xmm10, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm11[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm11[1]
|
||||
; SSE-NEXT: movaps %xmm10, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 48(%rcx), %xmm0
|
||||
; SSE-NEXT: movaps %xmm15, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; SSE-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm15 = xmm15[1],xmm0[1]
|
||||
; SSE-NEXT: movaps %xmm15, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: movaps 64(%rdi), %xmm15
|
||||
; SSE-NEXT: movaps 64(%rsi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm15, %xmm0
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm15 = xmm15[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 64(%rdx), %xmm11
|
||||
; SSE-NEXT: movaps 64(%rcx), %xmm2
|
||||
; SSE-NEXT: movaps %xmm11, %xmm14
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm14 = xmm14[0],xmm2[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm11 = xmm11[1],xmm2[1]
|
||||
; SSE-NEXT: movaps 80(%rdi), %xmm9
|
||||
; SSE-NEXT: movaps 80(%rsi), %xmm0
|
||||
; SSE-NEXT: movaps %xmm9, %xmm13
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm13 = xmm13[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm9 = xmm9[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 80(%rdx), %xmm10
|
||||
; SSE-NEXT: movaps 80(%rcx), %xmm0
|
||||
; SSE-NEXT: movaps %xmm10, %xmm12
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm12 = xmm12[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm10 = xmm10[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 96(%rdi), %xmm7
|
||||
; SSE-NEXT: movaps 96(%rsi), %xmm1
|
||||
; SSE-NEXT: movaps %xmm7, %xmm8
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm8 = xmm8[0],xmm1[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm7 = xmm7[1],xmm1[1]
|
||||
; SSE-NEXT: movaps 96(%rdx), %xmm5
|
||||
; SSE-NEXT: movaps 96(%rcx), %xmm0
|
||||
; SSE-NEXT: movaps %xmm5, %xmm6
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm6 = xmm6[0],xmm0[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm5 = xmm5[1],xmm0[1]
|
||||
; SSE-NEXT: movaps 112(%rdi), %xmm0
|
||||
; SSE-NEXT: movaps 112(%rsi), %xmm3
|
||||
; SSE-NEXT: movaps %xmm0, %xmm2
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm3[1]
|
||||
; SSE-NEXT: movaps 112(%rdx), %xmm3
|
||||
; SSE-NEXT: movaps 112(%rcx), %xmm4
|
||||
; SSE-NEXT: movaps %xmm3, %xmm1
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm4[0]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm3 = xmm3[1],xmm4[1]
|
||||
; SSE-NEXT: movaps %xmm3, 496(%r8)
|
||||
; SSE-NEXT: movaps %xmm0, 480(%r8)
|
||||
; SSE-NEXT: movaps %xmm1, 464(%r8)
|
||||
; SSE-NEXT: movaps %xmm2, 448(%r8)
|
||||
; SSE-NEXT: movaps %xmm5, 432(%r8)
|
||||
; SSE-NEXT: movaps %xmm7, 416(%r8)
|
||||
; SSE-NEXT: movaps %xmm6, 400(%r8)
|
||||
; SSE-NEXT: movaps %xmm8, 384(%r8)
|
||||
; SSE-NEXT: movaps %xmm10, 368(%r8)
|
||||
; SSE-NEXT: movaps %xmm9, 352(%r8)
|
||||
; SSE-NEXT: movaps %xmm12, 336(%r8)
|
||||
; SSE-NEXT: movaps %xmm13, 320(%r8)
|
||||
; SSE-NEXT: movaps %xmm11, 304(%r8)
|
||||
; SSE-NEXT: movaps %xmm15, 288(%r8)
|
||||
; SSE-NEXT: movaps %xmm14, 272(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 256(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 240(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 224(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 208(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 192(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 176(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 160(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 144(%r8)
|
||||
; SSE-NEXT: movaps (%rsp), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 128(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 112(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 96(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 80(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 64(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 48(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 32(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, 16(%r8)
|
||||
; SSE-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; SSE-NEXT: movaps %xmm0, (%r8)
|
||||
; SSE-NEXT: addq $152, %rsp
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: store_i64_stride4_vf16:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: subq $152, %rsp
|
||||
; AVX1-NEXT: vmovaps 96(%rdx), %ymm12
|
||||
; AVX1-NEXT: vmovaps 64(%rdx), %ymm1
|
||||
; AVX1-NEXT: vmovaps 32(%rdx), %ymm2
|
||||
; AVX1-NEXT: vmovaps (%rdx), %ymm3
|
||||
; AVX1-NEXT: vmovaps 96(%rcx), %ymm13
|
||||
; AVX1-NEXT: vmovaps 64(%rcx), %ymm5
|
||||
; AVX1-NEXT: vmovaps 32(%rcx), %ymm4
|
||||
; AVX1-NEXT: vmovaps (%rcx), %ymm6
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm8 = ymm3[1],ymm6[1],ymm3[3],ymm6[3]
|
||||
; AVX1-NEXT: vmovaps 16(%rsi), %xmm0
|
||||
; AVX1-NEXT: vmovaps 16(%rdi), %xmm7
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm9 = xmm7[1],xmm0[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm8 = ymm9[0,1,2,3],ymm8[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm8, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm3 = ymm3[0],ymm6[0],ymm3[2],ymm6[2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm7[0],xmm0[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm3[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm2[1],ymm4[1],ymm2[3],ymm4[3]
|
||||
; AVX1-NEXT: vmovaps 48(%rsi), %xmm3
|
||||
; AVX1-NEXT: vmovaps 48(%rdi), %xmm6
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm7 = xmm6[1],xmm3[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm7[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm2[0],ymm4[0],ymm2[2],ymm4[2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm2 = xmm6[0],xmm3[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm1[1],ymm5[1],ymm1[3],ymm5[3]
|
||||
; AVX1-NEXT: vmovaps 80(%rsi), %xmm2
|
||||
; AVX1-NEXT: vmovaps 80(%rdi), %xmm3
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm4 = xmm3[1],xmm2[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm4[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm1[0],ymm5[0],ymm1[2],ymm5[2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm3[0],xmm2[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm12[1],ymm13[1],ymm12[3],ymm13[3]
|
||||
; AVX1-NEXT: vmovaps 112(%rsi), %xmm1
|
||||
; AVX1-NEXT: vmovaps 112(%rdi), %xmm2
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm2[1],xmm1[1]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm12[0],ymm13[0],ymm12[2],ymm13[2]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm1 = xmm2[0],xmm1[0]
|
||||
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
|
||||
; AVX1-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX1-NEXT: vmovaps 64(%rsi), %xmm2
|
||||
; AVX1-NEXT: vmovaps 64(%rdi), %xmm3
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm3[1],xmm2[1]
|
||||
; AVX1-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX1-NEXT: vmovaps 32(%rcx), %xmm4
|
||||
; AVX1-NEXT: vmovaps 64(%rcx), %xmm5
|
||||
; AVX1-NEXT: vmovaps 64(%rdx), %xmm7
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm15 = xmm7[1],xmm5[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm14 = xmm3[0],xmm2[0]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm13 = xmm7[0],xmm5[0]
|
||||
; AVX1-NEXT: vmovaps 32(%rsi), %xmm5
|
||||
; AVX1-NEXT: vmovaps 32(%rdi), %xmm7
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm12 = xmm7[1],xmm5[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm10 = xmm7[0],xmm5[0]
|
||||
; AVX1-NEXT: vmovaps 32(%rdx), %xmm7
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm11 = xmm7[1],xmm4[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm9 = xmm7[0],xmm4[0]
|
||||
; AVX1-NEXT: vmovaps 96(%rsi), %xmm7
|
||||
; AVX1-NEXT: vmovaps 96(%rdi), %xmm0
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm8 = xmm0[1],xmm7[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm6 = xmm0[0],xmm7[0]
|
||||
; AVX1-NEXT: vmovaps 96(%rcx), %xmm7
|
||||
; AVX1-NEXT: vmovaps 96(%rdx), %xmm0
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm5 = xmm0[1],xmm7[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm4 = xmm0[0],xmm7[0]
|
||||
; AVX1-NEXT: vmovaps (%rsi), %xmm7
|
||||
; AVX1-NEXT: vmovaps (%rdi), %xmm0
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm0[1],xmm7[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm2 = xmm0[0],xmm7[0]
|
||||
; AVX1-NEXT: vmovaps (%rcx), %xmm7
|
||||
; AVX1-NEXT: vmovaps (%rdx), %xmm0
|
||||
; AVX1-NEXT: vunpckhpd {{.*#+}} xmm1 = xmm0[1],xmm7[1]
|
||||
; AVX1-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm7[0]
|
||||
; AVX1-NEXT: vmovaps %xmm0, 16(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm2, (%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm1, 48(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm3, 32(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm4, 400(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm6, 384(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm5, 432(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm8, 416(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm9, 144(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm10, 128(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm11, 176(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm12, 160(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm13, 272(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm14, 256(%r8)
|
||||
; AVX1-NEXT: vmovaps %xmm15, 304(%r8)
|
||||
; AVX1-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; AVX1-NEXT: vmovaps %xmm0, 288(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 448(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 480(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 320(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 352(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 192(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 224(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 64(%r8)
|
||||
; AVX1-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX1-NEXT: vmovaps %ymm0, 96(%r8)
|
||||
; AVX1-NEXT: addq $152, %rsp
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: store_i64_stride4_vf16:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: subq $152, %rsp
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %ymm0
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %ymm5
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %ymm3
|
||||
; AVX2-NEXT: vmovaps (%rdi), %ymm1
|
||||
; AVX2-NEXT: vmovaps 96(%rsi), %ymm7
|
||||
; AVX2-NEXT: vmovaps 64(%rsi), %ymm6
|
||||
; AVX2-NEXT: vmovaps 32(%rsi), %ymm4
|
||||
; AVX2-NEXT: vmovaps (%rsi), %ymm2
|
||||
; AVX2-NEXT: vmovaps 96(%rdx), %ymm9
|
||||
; AVX2-NEXT: vmovaps 64(%rdx), %ymm10
|
||||
; AVX2-NEXT: vmovaps 32(%rdx), %ymm11
|
||||
; AVX2-NEXT: vmovaps (%rdx), %ymm12
|
||||
; AVX2-NEXT: vmovaps 96(%rcx), %ymm13
|
||||
; AVX2-NEXT: vmovaps (%rcx), %ymm14
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm8 = ymm12[1],ymm14[1],ymm12[3],ymm14[3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm15 = ymm1[1],ymm2[1],ymm1[3],ymm2[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm8 = ymm15[2,3],ymm8[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm8, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 64(%rcx), %ymm15
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm12 = ymm12[0],ymm14[0],ymm12[2],ymm14[2]
|
||||
; AVX2-NEXT: vmovaps 32(%rcx), %ymm14
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm1 = ymm1[0],ymm2[0],ymm1[2],ymm2[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm1[2,3],ymm12[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm2 = ymm11[1],ymm14[1],ymm11[3],ymm14[3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm12 = ymm3[1],ymm4[1],ymm3[3],ymm4[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm12[2,3],ymm2[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm11 = ymm11[0],ymm14[0],ymm11[2],ymm14[2]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm3 = ymm3[0],ymm4[0],ymm3[2],ymm4[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm3[2,3],ymm11[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm4 = ymm10[1],ymm15[1],ymm10[3],ymm15[3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm11 = ymm5[1],ymm6[1],ymm5[3],ymm6[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm11[2,3],ymm4[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm10 = ymm10[0],ymm15[0],ymm10[2],ymm15[2]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm5 = ymm5[0],ymm6[0],ymm5[2],ymm6[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm5[2,3],ymm10[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm6 = ymm9[1],ymm13[1],ymm9[3],ymm13[3]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} ymm10 = ymm0[1],ymm7[1],ymm0[3],ymm7[3]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm10[2,3],ymm6[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm9 = ymm9[0],ymm13[0],ymm9[2],ymm13[2]
|
||||
; AVX2-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm7[0],ymm0[2],ymm7[2]
|
||||
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm9[2,3]
|
||||
; AVX2-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
||||
; AVX2-NEXT: vmovaps 32(%rsi), %xmm2
|
||||
; AVX2-NEXT: vmovaps 64(%rsi), %xmm3
|
||||
; AVX2-NEXT: vmovaps 32(%rdi), %xmm4
|
||||
; AVX2-NEXT: vmovaps 64(%rdi), %xmm5
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm5[1],xmm3[1]
|
||||
; AVX2-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
||||
; AVX2-NEXT: vmovaps 32(%rcx), %xmm6
|
||||
; AVX2-NEXT: vmovaps 64(%rcx), %xmm7
|
||||
; AVX2-NEXT: vmovaps 64(%rdx), %xmm0
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm14 = xmm5[0],xmm3[0]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm15 = xmm0[1],xmm7[1]
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm13 = xmm0[0],xmm7[0]
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm12 = xmm4[1],xmm2[1]
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm10 = xmm4[0],xmm2[0]
|
||||
; AVX2-NEXT: vmovaps 32(%rdx), %xmm4
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm11 = xmm4[1],xmm6[1]
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm9 = xmm4[0],xmm6[0]
|
||||
; AVX2-NEXT: vmovaps 96(%rsi), %xmm6
|
||||
; AVX2-NEXT: vmovaps 96(%rdi), %xmm0
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm8 = xmm0[1],xmm6[1]
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm7 = xmm0[0],xmm6[0]
|
||||
; AVX2-NEXT: vmovaps 96(%rcx), %xmm6
|
||||
; AVX2-NEXT: vmovaps 96(%rdx), %xmm0
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm5 = xmm0[1],xmm6[1]
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm4 = xmm0[0],xmm6[0]
|
||||
; AVX2-NEXT: vmovaps (%rsi), %xmm6
|
||||
; AVX2-NEXT: vmovaps (%rdi), %xmm0
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm0[1],xmm6[1]
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm2 = xmm0[0],xmm6[0]
|
||||
; AVX2-NEXT: vmovaps (%rcx), %xmm6
|
||||
; AVX2-NEXT: vmovaps (%rdx), %xmm0
|
||||
; AVX2-NEXT: vunpckhpd {{.*#+}} xmm1 = xmm0[1],xmm6[1]
|
||||
; AVX2-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm6[0]
|
||||
; AVX2-NEXT: vmovaps %xmm0, 16(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm2, (%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm1, 48(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm3, 32(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm4, 400(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm7, 384(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm5, 432(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm8, 416(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm9, 144(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm10, 128(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm11, 176(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm12, 160(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm13, 272(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm14, 256(%r8)
|
||||
; AVX2-NEXT: vmovaps %xmm15, 304(%r8)
|
||||
; AVX2-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
||||
; AVX2-NEXT: vmovaps %xmm0, 288(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 448(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 480(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 320(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 352(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 192(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 224(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 64(%r8)
|
||||
; AVX2-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
||||
; AVX2-NEXT: vmovaps %ymm0, 96(%r8)
|
||||
; AVX2-NEXT: addq $152, %rsp
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: store_i64_stride4_vf16:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vmovdqu64 (%rdi), %zmm0
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdi), %zmm1
|
||||
; AVX512-NEXT: vmovdqu64 (%rsi), %zmm2
|
||||
; AVX512-NEXT: vmovdqu64 64(%rsi), %zmm3
|
||||
; AVX512-NEXT: vmovdqu64 (%rdx), %zmm4
|
||||
; AVX512-NEXT: vmovdqu64 64(%rdx), %zmm5
|
||||
; AVX512-NEXT: vmovdqu64 (%rcx), %zmm6
|
||||
; AVX512-NEXT: vmovdqu64 64(%rcx), %zmm7
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm8 = <u,u,2,10,u,u,3,11>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm9
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm8, %zmm9
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm10 = <2,10,u,u,3,11,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm11
|
||||
; AVX512-NEXT: vpermt2q %zmm2, %zmm10, %zmm11
|
||||
; AVX512-NEXT: movb $-52, %al
|
||||
; AVX512-NEXT: kmovd %eax, %k1
|
||||
; AVX512-NEXT: vmovdqa64 %zmm9, %zmm11 {%k1}
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm9 = <u,u,0,8,u,u,1,9>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm12
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm9, %zmm12
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm13 = <0,8,u,u,1,9,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm14
|
||||
; AVX512-NEXT: vpermt2q %zmm2, %zmm13, %zmm14
|
||||
; AVX512-NEXT: vmovdqa64 %zmm12, %zmm14 {%k1}
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm12 = <u,u,6,14,u,u,7,15>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm15
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm12, %zmm15
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm16 = <6,14,u,u,7,15,u,u>
|
||||
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm17
|
||||
; AVX512-NEXT: vpermt2q %zmm2, %zmm16, %zmm17
|
||||
; AVX512-NEXT: vmovdqa64 %zmm15, %zmm17 {%k1}
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm15 = <u,u,4,12,u,u,5,13>
|
||||
; AVX512-NEXT: vpermt2q %zmm6, %zmm15, %zmm4
|
||||
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm6 = <4,12,u,u,5,13,u,u>
|
||||
; AVX512-NEXT: vpermt2q %zmm2, %zmm6, %zmm0
|
||||
; AVX512-NEXT: vmovdqa64 %zmm4, %zmm0 {%k1}
|
||||
; AVX512-NEXT: vpermi2q %zmm7, %zmm5, %zmm8
|
||||
; AVX512-NEXT: vpermi2q %zmm3, %zmm1, %zmm10
|
||||
; AVX512-NEXT: vmovdqa64 %zmm8, %zmm10 {%k1}
|
||||
; AVX512-NEXT: vpermi2q %zmm7, %zmm5, %zmm9
|
||||
; AVX512-NEXT: vpermi2q %zmm3, %zmm1, %zmm13
|
||||
; AVX512-NEXT: vmovdqa64 %zmm9, %zmm13 {%k1}
|
||||
; AVX512-NEXT: vpermi2q %zmm7, %zmm5, %zmm12
|
||||
; AVX512-NEXT: vpermi2q %zmm3, %zmm1, %zmm16
|
||||
; AVX512-NEXT: vmovdqa64 %zmm12, %zmm16 {%k1}
|
||||
; AVX512-NEXT: vpermt2q %zmm7, %zmm15, %zmm5
|
||||
; AVX512-NEXT: vpermt2q %zmm3, %zmm6, %zmm1
|
||||
; AVX512-NEXT: vmovdqa64 %zmm5, %zmm1 {%k1}
|
||||
; AVX512-NEXT: vmovdqu64 %zmm1, 384(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm16, 448(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm13, 256(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm10, 320(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm0, 128(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm17, 192(%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm14, (%r8)
|
||||
; AVX512-NEXT: vmovdqu64 %zmm11, 64(%r8)
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%in.vec0 = load <16 x i64>, <16 x i64>* %in.vecptr0, align 32
|
||||
%in.vec1 = load <16 x i64>, <16 x i64>* %in.vecptr1, align 32
|
||||
%in.vec2 = load <16 x i64>, <16 x i64>* %in.vecptr2, align 32
|
||||
%in.vec3 = load <16 x i64>, <16 x i64>* %in.vecptr3, align 32
|
||||
|
||||
%concat01 = shufflevector <16 x i64> %in.vec0, <16 x i64> %in.vec1, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
|
||||
%concat23 = shufflevector <16 x i64> %in.vec2, <16 x i64> %in.vec3, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
|
||||
%concat0123 = shufflevector <32 x i64> %concat01, <32 x i64> %concat23, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
|
||||
%interleaved.vec = shufflevector <64 x i64> %concat0123, <64 x i64> poison, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>
|
||||
|
||||
store <64 x i64> %interleaved.vec, <64 x i64>* %out.vec, align 32
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue