forked from OSchip/llvm-project
3fc933af8b
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
|
||
|---|---|---|
| .. | ||
| simple.ll | ||
| simple32.ll | ||
| start-unk.ll | ||