3
我有以下IR：爲什麼不LLVM SIMD向量化此代碼？
; ModuleID = 'vec.ir'
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-darwin15.3.0"
define void @patch(i64) {
entry:
%1 = load float, float* inttoptr (i64 4388240000 to float*)
%2 = load float, float* inttoptr (i64 4387644544 to float*)
%3 = fadd float %1, %2
%4 = load float, float* inttoptr (i64 4387729024 to float*)
%5 = fadd float %1, %4
%6 = load float, float* inttoptr (i64 4387730560 to float*)
%7 = fadd float %1, %6
%8 = load float, float* inttoptr (i64 4387513984 to float*)
%9 = fadd float %1, %8
store float %3, float* inttoptr (i64 4371309760 to float*)
call void @__tickValue(i64 105553117467608, i64 %0)
store float %5, float* inttoptr (i64 4371851456 to float*)
call void @__tickValue(i64 105553117465688, i64 %0)
store float %7, float* inttoptr (i64 4371574976 to float*)
call void @__tickValue(i64 105553117465528, i64 %0)
store float %9, float* inttoptr (i64 4371576512 to float*)
call void @__tickValue(i64 105553117466648, i64 %0)
ret void
}
declare void @__tickValue(i64, i64)
當我運行/usr/local/opt/llvm/bin/opt -S -O3 vec.ir > vec-opt.ir，我得到：
; ModuleID = 'vec.ir'
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-darwin15.3.0"
define void @patch(i64) {
entry:
%1 = load float, float* inttoptr (i64 4388240000 to float*), align 128
%2 = load float, float* inttoptr (i64 4387644544 to float*), align 128
%3 = fadd float %1, %2
%4 = load float, float* inttoptr (i64 4387729024 to float*), align 128
%5 = fadd float %1, %4
%6 = load float, float* inttoptr (i64 4387730560 to float*), align 128
%7 = fadd float %1, %6
%8 = load float, float* inttoptr (i64 4387513984 to float*), align 128
%9 = fadd float %1, %8
store float %3, float* inttoptr (i64 4371309760 to float*), align 64
tail call void @__tickValue(i64 105553117467608, i64 %0)
store float %5, float* inttoptr (i64 4371851456 to float*), align 64
tail call void @__tickValue(i64 105553117465688, i64 %0)
store float %7, float* inttoptr (i64 4371574976 to float*), align 64
tail call void @__tickValue(i64 105553117465528, i64 %0)
store float %9, float* inttoptr (i64 4371576512 to float*), align 64
tail call void @__tickValue(i64 105553117466648, i64 %0)
ret void
}
declare void @__tickValue(i64, i64)
每http://llvm.org/docs/Vectorizers.html#the-slp-vectorizer，我希望在fadd指令將被合併。
如何確定有關優化程序未進行向量化的更多信息？