It seems offsets are compiled wrong with our compiler
Being a potential gcc bug I'll subscribe doko and add a bug task.
--- bad-avx512-enabled +++ good-avx512-disabled - vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x0] + vmovdqu xmm0,XMMWORD PTR [rax*8+0x0] vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x10],0x1 vmovups XMMWORD PTR [rsi],xmm0 vextracti128 XMMWORD PTR [rsi+0x10],ymm0,0x1 - vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x2] + vmovdqu xmm0,XMMWORD PTR [rax*8+0x20] vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x30],0x1 vmovups XMMWORD PTR [rsi+0x20],xmm0 vextracti128 XMMWORD PTR [rsi+0x30],ymm0,0x1 - vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x4] + vmovdqu xmm0,XMMWORD PTR [rax*8+0x40] vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x50],0x1 vmovups XMMWORD PTR [rsi+0x40],xmm0 vextracti128 XMMWORD PTR [rsi+0x50],ymm0,0x1 - vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x6] + vmovdqu xmm0,XMMWORD PTR [rax*8+0x60] vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x70],0x1 vmovups XMMWORD PTR [rsi+0x60],xmm0 vextracti128 XMMWORD PTR [rsi+0x70],ymm0,0x1
I know I'll need to ask for or recreate on my own a repro for Doko to take a look ... time arr
It seems offsets are compiled wrong with our compiler
Being a potential gcc bug I'll subscribe doko and add a bug task.
--- bad-avx512-enabled disabled
+++ good-avx512-
- vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x0]
+ vmovdqu xmm0,XMMWORD PTR [rax*8+0x0]
vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x10],0x1
vmovups XMMWORD PTR [rsi],xmm0
vextracti128 XMMWORD PTR [rsi+0x10],ymm0,0x1
- vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x2]
+ vmovdqu xmm0,XMMWORD PTR [rax*8+0x20]
vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x30],0x1
vmovups XMMWORD PTR [rsi+0x20],xmm0
vextracti128 XMMWORD PTR [rsi+0x30],ymm0,0x1
- vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x4]
+ vmovdqu xmm0,XMMWORD PTR [rax*8+0x40]
vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x50],0x1
vmovups XMMWORD PTR [rsi+0x40],xmm0
vextracti128 XMMWORD PTR [rsi+0x50],ymm0,0x1
- vmovdqu8 xmm0,XMMWORD PTR [rax*8+0x6]
+ vmovdqu xmm0,XMMWORD PTR [rax*8+0x60]
vinserti128 ymm0,ymm0,XMMWORD PTR [rax*8+0x70],0x1
vmovups XMMWORD PTR [rsi+0x60],xmm0
vextracti128 XMMWORD PTR [rsi+0x70],ymm0,0x1
I know I'll need to ask for or recreate on my own a repro for Doko to take a look ... time arr