mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-28 04:33:05 +00:00
5f0d9dbdf4
This matters for example in following matrix multiply:
int **mmult(int rows, int cols, int **m1, int **m2, int **m3) {
int i, j, k, val;
for (i=0; i<rows; i++) {
for (j=0; j<cols; j++) {
val = 0;
for (k=0; k<cols; k++) {
val += m1[i][k] * m2[k][j];
}
m3[i][j] = val;
}
}
return(m3);
}
Taken from the test-suite benchmark Shootout.
We estimate the cost of the multiply to be 2 while we generate 9 instructions
for it and end up being quite a bit slower than the scalar version (48% on my
machine).
Also, properly differentiate between avx1 and avx2. On avx-1 we still split the
vector into 2 128bits and handle the subvector muls like above with 9
instructions.
Only on avx-2 will we have a cost of 9 for v4i64.
I changed the test case in test/Transforms/LoopVectorize/X86/avx1.ll to use an
add instead of a mul because with a mul we now no longer vectorize. I did
verify that the mul would be indeed more expensive when vectorized with 3
kernels:
for (i ...)
r += a[i] * 3;
for (i ...)
m1[i] = m1[i] * 3; // This matches the test case in avx1.ll
and a matrix multiply.
In each case the vectorized version was considerably slower.
radar://13304919
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176403 91177308-0d34-0410-b5e6-96231b3b80d8
50 lines
1.9 KiB
LLVM
50 lines
1.9 KiB
LLVM
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.8.0"
|
|
|
|
;CHECK: @read_mod_write_single_ptr
|
|
;CHECK: load <8 x float>
|
|
;CHECK: ret i32
|
|
define i32 @read_mod_write_single_ptr(float* nocapture %a, i32 %n) nounwind uwtable ssp {
|
|
%1 = icmp sgt i32 %n, 0
|
|
br i1 %1, label %.lr.ph, label %._crit_edge
|
|
|
|
.lr.ph: ; preds = %0, %.lr.ph
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
|
|
%2 = getelementptr inbounds float* %a, i64 %indvars.iv
|
|
%3 = load float* %2, align 4
|
|
%4 = fmul float %3, 3.000000e+00
|
|
store float %4, float* %2, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %n
|
|
br i1 %exitcond, label %._crit_edge, label %.lr.ph
|
|
|
|
._crit_edge: ; preds = %.lr.ph, %0
|
|
ret i32 undef
|
|
}
|
|
|
|
|
|
;CHECK: @read_mod_i64
|
|
;CHECK: load <2 x i64>
|
|
;CHECK: ret i32
|
|
define i32 @read_mod_i64(i64* nocapture %a, i32 %n) nounwind uwtable ssp {
|
|
%1 = icmp sgt i32 %n, 0
|
|
br i1 %1, label %.lr.ph, label %._crit_edge
|
|
|
|
.lr.ph: ; preds = %0, %.lr.ph
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
|
|
%2 = getelementptr inbounds i64* %a, i64 %indvars.iv
|
|
%3 = load i64* %2, align 4
|
|
%4 = add i64 %3, 3
|
|
store i64 %4, i64* %2, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %n
|
|
br i1 %exitcond, label %._crit_edge, label %.lr.ph
|
|
|
|
._crit_edge: ; preds = %.lr.ph, %0
|
|
ret i32 undef
|
|
}
|