Fangrui Song 3fc933af8b [AlignmentFromAssumptions] getNewAlignmentDiff(): use getURemExpr() ... The alignment is calculated incorrectly, thus sometimes it doesn't generate aligned mov instructions, as shown by the example below: ``` // b.cc typedef long long index; extern "C" index g_tid; extern "C" index g_num; void add3(float* __restrict__ a, float* __restrict__ b, float* __restrict__ c) { index n = 64*1024; index m = 16*1024; index k = 4*1024; index tid = g_tid; index num = g_num; __builtin_assume_aligned(a, 32); __builtin_assume_aligned(b, 32); __builtin_assume_aligned(c, 32); for (index i0=tid*k; i0<m; i0+=num*k) for (index i1=0; i1<n*m; i1+=m) for (index i2=0; i2<k; i2++) c[i1+i0+i2] = b[i0+i2] + a[i1+i0+i2]; } ``` Compile with `clang b.cc -Ofast -march=skylake -mavx2 -S` ``` vmovaps -224(%rdi,%rbx,4), %ymm0 vmovups -192(%rdi,%rbx,4), %ymm1 # should be movaps vmovups -160(%rdi,%rbx,4), %ymm2 # should be movaps vmovups -128(%rdi,%rbx,4), %ymm3 # should be movaps vaddps -224(%rsi,%rbx,4), %ymm0, %ymm0 vaddps -192(%rsi,%rbx,4), %ymm1, %ymm1 vaddps -160(%rsi,%rbx,4), %ymm2, %ymm2 vaddps -128(%rsi,%rbx,4), %ymm3, %ymm3 vmovaps %ymm0, -224(%rdx,%rbx,4) vmovups %ymm1, -192(%rdx,%rbx,4) # should be movaps vmovups %ymm2, -160(%rdx,%rbx,4) # should be movaps vmovups %ymm3, -128(%rdx,%rbx,4) # should be movaps ``` Differential Revision: https://reviews.llvm.org/D66575 Patch by Dun Liang llvm-svn: 369723		2019-08-23 02:17:04 +00:00
..
simple.ll	[AlignmentFromAssumptions] getNewAlignmentDiff(): use getURemExpr()	2019-08-23 02:17:04 +00:00
simple32.ll	…
start-unk.ll	…