summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorEli Friedman <eli.friedman@gmail.com>2010-06-03 01:47:31 +0000
committerEli Friedman <eli.friedman@gmail.com>2010-06-03 01:47:31 +0000
commitdb1bf34178aec96559cf2e7190accc484c85d3e2 (patch)
tree7043fe17e284859f1fd9fc71ff3284bedca1f8ec
parenta04a2c0a50f8772614070b37d2407f9df50d93bc (diff)
downloadllvm-db1bf34178aec96559cf2e7190accc484c85d3e2.tar.gz
llvm-db1bf34178aec96559cf2e7190accc484c85d3e2.tar.bz2
llvm-db1bf34178aec96559cf2e7190accc484c85d3e2.tar.xz
Remove some already-fixed README entries.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@105377 91177308-0d34-0410-b5e6-96231b3b80d8
-rw-r--r--lib/Target/X86/README-SSE.txt87
1 files changed, 1 insertions, 86 deletions
diff --git a/lib/Target/X86/README-SSE.txt b/lib/Target/X86/README-SSE.txt
index 8f2db0059a..d761bde646 100644
--- a/lib/Target/X86/README-SSE.txt
+++ b/lib/Target/X86/README-SSE.txt
@@ -66,12 +66,6 @@ LBB_X_2:
//===---------------------------------------------------------------------===//
-It's not clear whether we should use pxor or xorps / xorpd to clear XMM
-registers. The choice may depend on subtarget information. We should do some
-more experiments on different x86 machines.
-
-//===---------------------------------------------------------------------===//
-
Lower memcpy / memset to a series of SSE 128 bit move instructions when it's
feasible.
@@ -95,35 +89,6 @@ Perhaps use pxor / xorp* to clear a XMM register first?
//===---------------------------------------------------------------------===//
-How to decide when to use the "floating point version" of logical ops? Here are
-some code fragments:
-
- movaps LCPI5_5, %xmm2
- divps %xmm1, %xmm2
- mulps %xmm2, %xmm3
- mulps 8656(%ecx), %xmm3
- addps 8672(%ecx), %xmm3
- andps LCPI5_6, %xmm2
- andps LCPI5_1, %xmm3
- por %xmm2, %xmm3
- movdqa %xmm3, (%edi)
-
- movaps LCPI5_5, %xmm1
- divps %xmm0, %xmm1
- mulps %xmm1, %xmm3
- mulps 8656(%ecx), %xmm3
- addps 8672(%ecx), %xmm3
- andps LCPI5_6, %xmm1
- andps LCPI5_1, %xmm3
- orps %xmm1, %xmm3
- movaps %xmm3, 112(%esp)
- movaps %xmm3, (%ebx)
-
-Due to some minor source change, the later case ended up using orps and movaps
-instead of por and movdqa. Does it matter?
-
-//===---------------------------------------------------------------------===//
-
X86RegisterInfo::copyRegToReg() returns X86::MOVAPSrr for VR128. Is it possible
to choose between movaps, movapd, and movdqa based on types of source and
destination?
@@ -222,41 +187,6 @@ It also exposes some other problems. See MOV32ri -3 and the spills.
//===---------------------------------------------------------------------===//
-http://gcc.gnu.org/bugzilla/show_bug.cgi?id=25500
-
-LLVM is producing bad code.
-
-LBB_main_4: # cond_true44
- addps %xmm1, %xmm2
- subps %xmm3, %xmm2
- movaps (%ecx), %xmm4
- movaps %xmm2, %xmm1
- addps %xmm4, %xmm1
- addl $16, %ecx
- incl %edx
- cmpl $262144, %edx
- movaps %xmm3, %xmm2
- movaps %xmm4, %xmm3
- jne LBB_main_4 # cond_true44
-
-There are two problems. 1) No need to two loop induction variables. We can
-compare against 262144 * 16. 2) Known register coalescer issue. We should
-be able eliminate one of the movaps:
-
- addps %xmm2, %xmm1 <=== Commute!
- subps %xmm3, %xmm1
- movaps (%ecx), %xmm4
- movaps %xmm1, %xmm1 <=== Eliminate!
- addps %xmm4, %xmm1
- addl $16, %ecx
- incl %edx
- cmpl $262144, %edx
- movaps %xmm3, %xmm2
- movaps %xmm4, %xmm3
- jne LBB_main_4 # cond_true44
-
-//===---------------------------------------------------------------------===//
-
Consider:
__m128 test(float a) {
@@ -326,22 +256,6 @@ elements are fixed zeros.
//===---------------------------------------------------------------------===//
-__m128d test1( __m128d A, __m128d B) {
- return _mm_shuffle_pd(A, B, 0x3);
-}
-
-compiles to
-
-shufpd $3, %xmm1, %xmm0
-
-Perhaps it's better to use unpckhpd instead?
-
-unpckhpd %xmm1, %xmm0
-
-Don't know if unpckhpd is faster. But it is shorter.
-
-//===---------------------------------------------------------------------===//
-
This code generates ugly code, probably due to costs being off or something:
define void @test(float* %P, <4 x float>* %P2 ) {
@@ -493,6 +407,7 @@ entry:
%tmp20 = tail call i64 @ccoshf( float %tmp6, float %z.0 ) nounwind readonly
ret i64 %tmp20
}
+declare i64 @ccoshf(float %z.0, float %z.1) nounwind readonly
This currently compiles to: