From 1f1b0f748daf08c4364a34f0af5de692d023c29f Mon Sep 17 00:00:00 2001 From: Eli Friedman Date: Mon, 21 Dec 2009 08:03:16 +0000 Subject: [PATCH] A couple minor README updates. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91823 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Target/X86/README.txt | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/lib/Target/X86/README.txt b/lib/Target/X86/README.txt index 9b7aab801eb..afd9f53ea6b 100644 --- a/lib/Target/X86/README.txt +++ b/lib/Target/X86/README.txt @@ -123,20 +123,6 @@ when it can invert the result of the compare for free. //===---------------------------------------------------------------------===// -How about intrinsics? An example is: - *res = _mm_mulhi_epu16(*A, _mm_mul_epu32(*B, *C)); - -compiles to - pmuludq (%eax), %xmm0 - movl 8(%esp), %eax - movdqa (%eax), %xmm1 - pmulhuw %xmm0, %xmm1 - -The transformation probably requires a X86 specific pass or a DAG combiner -target specific hook. - -//===---------------------------------------------------------------------===// - In many cases, LLVM generates code like this: _test: @@ -1762,6 +1748,11 @@ LBB1_1: ## bb1 cmpl $150, %edi jne LBB1_1 ## bb1 +The issue is that we hoist the cast of "scaler" to long long outside of the +loop, the value comes into the loop as two values, and +RegsForValue::getCopyFromRegs doesn't know how to put an AssertSext on the +constructed BUILD_PAIR which represents the cast value. + //===---------------------------------------------------------------------===// Test instructions can be eliminated by using EFLAGS values from arithmetic -- 2.34.1