maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/lea-recursion.ll

47 lines
2.6 KiB
LLVM
Raw Normal View History

Enable MI Sched for x86. This changes the SelectionDAG scheduling preference to source order. Soon, the SelectionDAG scheduler can be bypassed saving a nice chunk of compile time. Performance differences that result from this change are often a consequence of register coalescing. The register coalescer is far from perfect. Bugs can be filed for deficiencies. On x86 SandyBridge/Haswell, the source order schedule is often preserved, particularly for small blocks. Register pressure is generally improved over the SD scheduler's ILP mode. However, we are still able to handle large blocks that require latency hiding, unlike the SD scheduler's BURR mode. MI scheduler also attempts to discover the critical path in single-block loops and adjust heuristics accordingly. The MI scheduler relies on the new machine model. This is currently unimplemented for AVX, so we may not be generating the best code yet. Unit tests are updated so they don't depend on SD scheduling heuristics. llvm-svn: 192750
2013-10-16 07:33:07 +08:00
; RUN: llc < %s -march=x86-64 | grep lea | count 13
When x86 addresses matching exceeds its recursion limit, check to see if the base register is already occupied before assuming it can be used. This fixes bogus code generation in the accompanying testcase. llvm-svn: 41049
2007-08-14 04:03:06 +08:00
; This testcase was written to demonstrate an instruction-selection problem,
; however it also happens to expose a limitation in the DAGCombiner's
; expression reassociation which causes it to miss opportunities for
; constant folding due to the intermediate adds having multiple uses.
; The Reassociate pass has similar limitations. If these limitations are
; fixed, the test commands above will need to be updated to expect fewer
; lea instructions.
@g0 = weak global [1000 x i32] zeroinitializer, align 32 ; <[1000 x i32]*> [#uses=8]
@g1 = weak global [1000 x i32] zeroinitializer, align 32 ; <[1000 x i32]*> [#uses=7]
define void @foo() {
entry:
%tmp4 = load i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 0) ; <i32> [#uses=1]
%tmp8 = load i32* getelementptr ([1000 x i32]* @g1, i32 0, i32 0) ; <i32> [#uses=1]
%tmp9 = add i32 %tmp4, 1 ; <i32> [#uses=1]
%tmp10 = add i32 %tmp9, %tmp8 ; <i32> [#uses=2]
store i32 %tmp10, i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 1)
%tmp8.1 = load i32* getelementptr ([1000 x i32]* @g1, i32 0, i32 1) ; <i32> [#uses=1]
%tmp9.1 = add i32 %tmp10, 1 ; <i32> [#uses=1]
%tmp10.1 = add i32 %tmp9.1, %tmp8.1 ; <i32> [#uses=2]
store i32 %tmp10.1, i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 2)
%tmp8.2 = load i32* getelementptr ([1000 x i32]* @g1, i32 0, i32 2) ; <i32> [#uses=1]
%tmp9.2 = add i32 %tmp10.1, 1 ; <i32> [#uses=1]
%tmp10.2 = add i32 %tmp9.2, %tmp8.2 ; <i32> [#uses=2]
store i32 %tmp10.2, i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 3)
%tmp8.3 = load i32* getelementptr ([1000 x i32]* @g1, i32 0, i32 3) ; <i32> [#uses=1]
%tmp9.3 = add i32 %tmp10.2, 1 ; <i32> [#uses=1]
%tmp10.3 = add i32 %tmp9.3, %tmp8.3 ; <i32> [#uses=2]
store i32 %tmp10.3, i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 4)
%tmp8.4 = load i32* getelementptr ([1000 x i32]* @g1, i32 0, i32 4) ; <i32> [#uses=1]
%tmp9.4 = add i32 %tmp10.3, 1 ; <i32> [#uses=1]
%tmp10.4 = add i32 %tmp9.4, %tmp8.4 ; <i32> [#uses=2]
store i32 %tmp10.4, i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 5)
%tmp8.5 = load i32* getelementptr ([1000 x i32]* @g1, i32 0, i32 5) ; <i32> [#uses=1]
%tmp9.5 = add i32 %tmp10.4, 1 ; <i32> [#uses=1]
%tmp10.5 = add i32 %tmp9.5, %tmp8.5 ; <i32> [#uses=2]
store i32 %tmp10.5, i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 6)
%tmp8.6 = load i32* getelementptr ([1000 x i32]* @g1, i32 0, i32 6) ; <i32> [#uses=1]
%tmp9.6 = add i32 %tmp10.5, 1 ; <i32> [#uses=1]
%tmp10.6 = add i32 %tmp9.6, %tmp8.6 ; <i32> [#uses=1]
store i32 %tmp10.6, i32* getelementptr ([1000 x i32]* @g0, i32 0, i32 7)
ret void
}