llvm-mirror/test/CodeGen/X86/combine-lds.ll

; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep fldl | count 1

define double @doload64(i64 %x) nounwind  {
	%tmp717 = bitcast i64 %x to double
	ret double %tmp717
}
For whatever the reason, x86 CallingConv::Fast (i.e. fastcc) was not passing scalar arguments in registers. This patch defines a new fastcc CC which is slightly different from the FastCall CC. In addition to passing integer arguments in ECX and EDX, it also specify doubles are passed in 8-byte slots which are 8-byte aligned (instead of 4-byte aligned). This avoids a potential performance hazard where doubles span cacheline boundaries. llvm-svn: 55807 2008-09-05 00:59:58 +02:00			`; RUN: llvm-as < %s \| llc -march=x86 -mattr=+sse2 \| grep fldl \| count 1`
Xform bitconvert(build_pair(load a, load b)) to a single load if the load locations are at the right offset from each other. llvm-svn: 51008 2008-05-13 01:04:07 +02:00
For whatever the reason, x86 CallingConv::Fast (i.e. fastcc) was not passing scalar arguments in registers. This patch defines a new fastcc CC which is slightly different from the FastCall CC. In addition to passing integer arguments in ECX and EDX, it also specify doubles are passed in 8-byte slots which are 8-byte aligned (instead of 4-byte aligned). This avoids a potential performance hazard where doubles span cacheline boundaries. llvm-svn: 55807 2008-09-05 00:59:58 +02:00			`define double @doload64(i64 %x) nounwind {`
Xform bitconvert(build_pair(load a, load b)) to a single load if the load locations are at the right offset from each other. llvm-svn: 51008 2008-05-13 01:04:07 +02:00			`%tmp717 = bitcast i64 %x to double`
			`ret double %tmp717`
			`}`