diff options
| author | Stefan Pintilie <stefanp@ca.ibm.com> | 2018-01-09 21:57:49 +0000 |
|---|---|---|
| committer | Stefan Pintilie <stefanp@ca.ibm.com> | 2018-01-09 21:57:49 +0000 |
| commit | 1712700842c03afcb9c3c758f95fa039f912ec02 (patch) | |
| tree | 222860eb62ec863f4181b52c3e9bb27523416dc0 /llvm/test | |
| parent | 07657a8d7faf7cf255858485453ed1e5a1bdc5cd (diff) | |
| download | bcm5719-llvm-1712700842c03afcb9c3c758f95fa039f912ec02.tar.gz bcm5719-llvm-1712700842c03afcb9c3c758f95fa039f912ec02.zip | |
[PowerPC] Manually schedule the prologue and epilogue
This patch makes the following changes to the schedule of instructions in the
prologue and epilogue.
The stack pointer update is moved down in the prologue so that the callee saves
do not have to wait for the update to happen.
Saving the lr is moved down in the prologue to hide the latency of the mflr.
The stack pointer is moved up in the epilogue so that restoring of the lr can
happen sooner.
The mtlr is moved up in the epilogue so that it is away form the blr at the end
of the epilogue. The latency of the mtlr can now be hidden by the loads of the
callee saved registers.
This commit is almost identical to this one: r322036 except that two warnings
that broke build bots have been fixed.
The revision number is D41737 as before.
llvm-svn: 322124
Diffstat (limited to 'llvm/test')
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll | 10 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/ppc-redzone-alignment-bug.ll | 8 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll | 16 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/tls_get_addr_clobbers.ll | 18 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/vsxD-Form-spills.ll | 50 |
5 files changed, 52 insertions, 50 deletions
diff --git a/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll b/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll index c72523f3593..8f0c78a7dfb 100644 --- a/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll +++ b/llvm/test/CodeGen/PowerPC/MCSE-caller-preserved-reg.ll @@ -15,12 +15,12 @@ define noalias i8* @_ZN2CC3funEv(%class.CC* %this) { ; CHECK-LABEL: _ZN2CC3funEv: ; CHECK: mflr 0 -; CHECK-NEXT: std 0, 16(1) -; CHECK-NEXT: stdu 1, -48(1) ; CHECK-NEXT: .cfi_def_cfa_offset 48 ; CHECK-NEXT: .cfi_offset lr, 16 ; CHECK-NEXT: .cfi_offset r30, -16 -; CHECK-NEXT: std 30, 32(1) +; CHECK-NEXT: std 30, -16(1) +; CHECK-NEXT: std 0, 16(1) +; CHECK-NEXT: stdu 1, -48(1) ; CHECK-NEXT: mr 30, 3 ; CHECK-NEXT: ld 12, 0(30) ; CHECK-NEXT: std 2, 24(1) @@ -38,11 +38,11 @@ define noalias i8* @_ZN2CC3funEv(%class.CC* %this) { ; CHECK-NEXT: mr 3, 30 ; CHECK-NEXT: bl _ZN2CC3barEPi ; CHECK-NEXT: nop -; CHECK: ld 30, 32(1) -; CHECK-NEXT: li 3, 0 +; CHECK: li 3, 0 ; CHECK-NEXT: addi 1, 1, 48 ; CHECK-NEXT: ld 0, 16(1) ; CHECK-NEXT: mtlr 0 +; CHECK: ld 30, -16(1) ; CHECK-NEXT: blr entry: %foo = getelementptr inbounds %class.CC, %class.CC* %this, i64 0, i32 0, i32 0 diff --git a/llvm/test/CodeGen/PowerPC/ppc-redzone-alignment-bug.ll b/llvm/test/CodeGen/PowerPC/ppc-redzone-alignment-bug.ll index 87b45beeab7..dce8b3ac5b8 100644 --- a/llvm/test/CodeGen/PowerPC/ppc-redzone-alignment-bug.ll +++ b/llvm/test/CodeGen/PowerPC/ppc-redzone-alignment-bug.ll @@ -16,12 +16,12 @@ entry: ; stfd 14, 416(1) ; After the fix by patch D34337: +; CHECK-LE:std 15, -280(1) +; CHECK-LE:stfd 14, -144(1) ; CHECK-LE: stdu 1, -528(1) -; CHECK-LE:std 15, 248(1) -; CHECK-LE:stfd 14, 384(1) +; CHECK-BE:std 15, -280(1) +; CHECK-BE:stfd 14, -144(1) ; CHECK-BE: stdu 1, -544(1) -; CHECK-BE:std 15, 264(1) -; CHECK-BE:stfd 14, 400(1) } define signext i32 @foo() { diff --git a/llvm/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll b/llvm/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll index 2bf4b0722f9..e4898c35888 100644 --- a/llvm/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll +++ b/llvm/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll @@ -110,7 +110,7 @@ declare i32 @doSomething(i32, i32*) ; ; Epilogue code. ; CHECK: mtlr {{[0-9]+}} -; CHECK-NEXT: blr +; CHECK: blr ; ; ENABLE: .[[ELSE_LABEL]]: # %if.else ; Shift second argument by one and store into returned register. @@ -171,7 +171,7 @@ declare i32 @something(...) ; Next BB ; CHECK: %for.end ; CHECK: mtlr {{[0-9]+}} -; CHECK-NEXT: blr +; CHECK: blr define i32 @freqSaveAndRestoreOutsideLoop2(i32 %cond) { entry: br label %for.preheader @@ -209,9 +209,9 @@ for.end: ; preds = %for.body ; Make sure we save the link register ; CHECK: mflr {{[0-9]+}} ; -; DISABLE: cmplwi 0, 3, 0 -; DISABLE-NEXT: std +; DISABLE: std ; DISABLE-NEXT: std +; DISABLE: cmplwi 0, 3, 0 ; DISABLE-NEXT: beq 0, .[[ELSE_LABEL:LBB[0-9_]+]] ; ; Loop preheader @@ -240,7 +240,7 @@ for.end: ; preds = %for.body ; DISABLE: .[[EPILOG_BB]]: # %if.end ; Epilog code ; CHECK: mtlr {{[0-9]+}} -; CHECK-NEXT: blr +; CHECK: blr ; ; ENABLE: .[[ELSE_LABEL]]: # %if.else ; Shift second argument by one and store into returned register. @@ -291,9 +291,9 @@ declare void @somethingElse(...) ; Make sure we save the link register ; CHECK: mflr {{[0-9]+}} ; -; DISABLE: cmplwi 0, 3, 0 -; DISABLE-NEXT: std +; DISABLE: std ; DISABLE-NEXT: std +; DISABLE: cmplwi 0, 3, 0 ; DISABLE-NEXT: beq 0, .[[ELSE_LABEL:LBB[0-9_]+]] ; ; CHECK: bl somethingElse @@ -322,7 +322,7 @@ declare void @somethingElse(...) ; ; Epilogue code. ; CHECK: mtlr {{[0-9]+}} -; CHECK-NEXT: blr +; CHECK: blr ; ; ENABLE: .[[ELSE_LABEL]]: # %if.else ; Shift second argument by one and store into returned register. diff --git a/llvm/test/CodeGen/PowerPC/tls_get_addr_clobbers.ll b/llvm/test/CodeGen/PowerPC/tls_get_addr_clobbers.ll index 108993fea95..632358ec861 100644 --- a/llvm/test/CodeGen/PowerPC/tls_get_addr_clobbers.ll +++ b/llvm/test/CodeGen/PowerPC/tls_get_addr_clobbers.ll @@ -6,7 +6,7 @@ define void @test_foo(i32* nocapture %x01, i32* nocapture %x02, i32* nocapture % entry: ; CHECK-LABEL: test_foo: -; CHECK: stdu 1, {{-?[0-9]+}}(1) +; CHECK-DAG: stdu 1, {{-?[0-9]+}}(1) ; CHECK-DAG: mr [[BACKUP_3:[0-9]+]], 3 ; CHECK-DAG: mr [[BACKUP_4:[0-9]+]], 4 ; CHECK-DAG: mr [[BACKUP_5:[0-9]+]], 5 @@ -15,14 +15,14 @@ entry: ; CHECK-DAG: mr [[BACKUP_8:[0-9]+]], 8 ; CHECK-DAG: mr [[BACKUP_9:[0-9]+]], 9 ; CHECK-DAG: mr [[BACKUP_10:[0-9]+]], 10 -; CHECK-DAG: std [[BACKUP_3]], {{[0-9]+}}(1) -; CHECK-DAG: std [[BACKUP_4]], {{[0-9]+}}(1) -; CHECK-DAG: std [[BACKUP_5]], {{[0-9]+}}(1) -; CHECK-DAG: std [[BACKUP_6]], {{[0-9]+}}(1) -; CHECK-DAG: std [[BACKUP_7]], {{[0-9]+}}(1) -; CHECK-DAG: std [[BACKUP_8]], {{[0-9]+}}(1) -; CHECK-DAG: std [[BACKUP_9]], {{[0-9]+}}(1) -; CHECK-DAG: std [[BACKUP_10]], {{[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_3]], {{-?[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_4]], {{-?[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_5]], {{-?[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_6]], {{-?[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_7]], {{-?[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_8]], {{-?[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_9]], {{-?[0-9]+}}(1) +; CHECK-DAG: std [[BACKUP_10]], {{-?[0-9]+}}(1) ; CHECK: bl __tls_get_addr ; CHECK-DAG: stw 3, 0([[BACKUP_3]]) ; CHECK-DAG: stw 3, 0([[BACKUP_4]]) diff --git a/llvm/test/CodeGen/PowerPC/vsxD-Form-spills.ll b/llvm/test/CodeGen/PowerPC/vsxD-Form-spills.ll index 92427f5ccde..b02c8aeba17 100644 --- a/llvm/test/CodeGen/PowerPC/vsxD-Form-spills.ll +++ b/llvm/test/CodeGen/PowerPC/vsxD-Form-spills.ll @@ -4,35 +4,37 @@ define <4 x i32> @testSpill(<4 x i32> %a, <4 x i32> %b) { ; CHECK-LABEL: testSpill: -; CHECK: li 11, 80 -; CHECK: li 12, 96 -; CHECK: li 3, 48 -; CHECK: li 10, 64 -; CHECK: stxvd2x 62, 1, 11 # 16-byte Folded Spill -; CHECK: stxvd2x 63, 1, 12 # 16-byte Folded Spill -; CHECK: stxvd2x 60, 1, 3 # 16-byte Folded Spill -; CHECK: stxvd2x 61, 1, 10 # 16-byte Folded Spill -; CHECK: li 9, 96 -; CHECK: li 10, 80 -; CHECK: li 11, 64 -; CHECK: li 12, 48 -; CHECK: lxvd2x 63, 1, 9 # 16-byte Folded Reload -; CHECK: lxvd2x 62, 1, 10 # 16-byte Folded Reload -; CHECK: lxvd2x 61, 1, 11 # 16-byte Folded Reload -; CHECK: lxvd2x 60, 1, 12 # 16-byte Folded Reload +; CHECK-DAG: li [[REG64:[0-9]+]], -64 +; CHECK-DAG: li [[REG48:[0-9]+]], -48 +; CHECK-DAG: li [[REG32:[0-9]+]], -32 +; CHECK-DAG: li [[REG16:[0-9]+]], -16 +; CHECK-NOT: li +; CHECK-DAG: stxvd2x 60, 1, [[REG64]] # 16-byte Folded Spill +; CHECK-DAG: stxvd2x 61, 1, [[REG48]] # 16-byte Folded Spill +; CHECK-DAG: stxvd2x 62, 1, [[REG32]] # 16-byte Folded Spill +; CHECK-DAG: stxvd2x 63, 1, [[REG16]] # 16-byte Folded Spill +; CHECK: std 0, 16(1) +; CHECK-DAG: li [[REG16:[0-9]+]], -16 +; CHECK-DAG: li [[REG32:[0-9]+]], -32 +; CHECK-DAG: li [[REG48:[0-9]+]], -48 +; CHECK-DAG: li [[REG64:[0-9]+]], -64 ; CHECK: mtlr 0 +; CHECK-DAG: lxvd2x 63, 1, [[REG16]] # 16-byte Folded Reload +; CHECK-DAG: lxvd2x 62, 1, [[REG32]] # 16-byte Folded Reload +; CHECK-DAG: lxvd2x 61, 1, [[REG48]] # 16-byte Folded Reload +; CHECK-DAG: lxvd2x 60, 1, [[REG64]] # 16-byte Folded Reload ; CHECK-NEXT: blr ; ; CHECK-PWR9-LABEL: testSpill: -; CHECK-PWR9: stxv 62, 80(1) # 16-byte Folded Spill -; CHECK-PWR9: stxv 63, 96(1) # 16-byte Folded Spill -; CHECK-PWR9: stxv 60, 48(1) # 16-byte Folded Spill -; CHECK-PWR9: stxv 61, 64(1) # 16-byte Folded Spill -; CHECK-PWR9: lxv 63, 96(1) # 16-byte Folded Reload -; CHECK-PWR9: lxv 62, 80(1) # 16-byte Folded Reload -; CHECK-PWR9: lxv 61, 64(1) # 16-byte Folded Reload -; CHECK-PWR9: lxv 60, 48(1) # 16-byte Folded Reload +; CHECK-PWR9-DAG: stxv 60, -64(1) # 16-byte Folded Spill +; CHECK-PWR9-DAG: stxv 61, -48(1) # 16-byte Folded Spill +; CHECK-PWR9-DAG: stxv 62, -32(1) # 16-byte Folded Spill +; CHECK-PWR9-DAG: stxv 63, -16(1) # 16-byte Folded Spill ; CHECK-PWR9: mtlr 0 +; CHECK-PWR9-DAG: lxv 63, -16(1) # 16-byte Folded Reload +; CHECK-PWR9-DAG: lxv 62, -32(1) # 16-byte Folded Reload +; CHECK-PWR9-DAG: lxv 61, -48(1) # 16-byte Folded Reload +; CHECK-PWR9-DAG: lxv 60, -64(1) # 16-byte Folded Reload ; CHECK-PWR9-NEXT: blr entry: |

