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/zext-fold.ll

42 lines
995 B
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 -mcpu=generic -march=x86 -enable-misched=false | FileCheck %s
Add a DAGCombine for (ext (binop (load x), cst)). llvm-svn: 133124
2011-06-16 09:15:49 +08:00
;; Simple case
define i32 @test1(i8 %x) nounwind readnone {
%A = and i8 %x, -32
%B = zext i8 %A to i32
ret i32 %B
}
; CHECK: test1
; CHECK: movzbl
Revert "[X86] Widen the 'AND' mask if doing so shrinks the encoding size" This reverts commit 245169 which miscompiles MultiSource/Applications/siod from LNT. llvm-svn: 245432
2015-08-19 19:35:10 +08:00
; CHECK-NEXT: andl {{.*}}224
Add a DAGCombine for (ext (binop (load x), cst)). llvm-svn: 133124
2011-06-16 09:15:49 +08:00
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
;; Multiple uses of %x but easily extensible.
Add a DAGCombine for (ext (binop (load x), cst)). llvm-svn: 133124
2011-06-16 09:15:49 +08:00
define i32 @test2(i8 %x) nounwind readnone {
%A = and i8 %x, -32
%B = zext i8 %A to i32
%C = or i8 %x, 63
%D = zext i8 %C to i32
%E = add i32 %B, %D
ret i32 %E
}
; CHECK: test2
; CHECK: movzbl
Revert "[X86] Widen the 'AND' mask if doing so shrinks the encoding size" This reverts commit 245169 which miscompiles MultiSource/Applications/siod from LNT. llvm-svn: 245432
2015-08-19 19:35:10 +08:00
; CHECK: andl $224
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
; CHECK: orl $63
Add a DAGCombine for (ext (binop (load x), cst)). llvm-svn: 133124
2011-06-16 09:15:49 +08:00
declare void @use(i32, i8)
;; Multiple uses of %x where we shouldn't extend the load.
define void @test3(i8 %x) nounwind readnone {
%A = and i8 %x, -32
%B = zext i8 %A to i32
call void @use(i32 %B, i8 %x)
ret void
}
; CHECK: test3
llvm/test/CodeGen/X86/zext-fold.ll: Relax an expression in stack offset. llvm-svn: 147928
2012-01-11 15:34:22 +08:00
; CHECK: movzbl {{[0-9]+}}(%esp), [[REGISTER:%e[a-z]{2}]]
There's no need to be so picky about the particular register. llvm-svn: 133189
2011-06-17 05:00:00 +08:00
; CHECK-NEXT: movl [[REGISTER]], 4(%esp)
Revert "[X86] Widen the 'AND' mask if doing so shrinks the encoding size" This reverts commit 245169 which miscompiles MultiSource/Applications/siod from LNT. llvm-svn: 245432
2015-08-19 19:35:10 +08:00
; CHECK-NEXT: andl $224, [[REGISTER]]
There's no need to be so picky about the particular register. llvm-svn: 133189
2011-06-17 05:00:00 +08:00
; CHECK-NEXT: movl [[REGISTER]], (%esp)
Commit the right set of tests for r133124. Sorry 'bout that! llvm-svn: 133133
2011-06-16 09:35:45 +08:00
; CHECK-NEXT: call{{.*}}use