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/Thumb2/aligned-spill.ll

96 lines
3.1 KiB
LLVM
Raw Normal View History

Enable aligned NEON spilling by default. Experiments show this to be a small speedup for modern ARM cores. llvm-svn: 147689
2012-01-07 06:19:37 +08:00
; RUN: llc < %s -mcpu=cortex-a8 -align-neon-spills=0 | FileCheck %s
; RUN: llc < %s -mcpu=cortex-a8 -align-neon-spills=1 | FileCheck %s --check-prefix=NEON
Heed spill slot alignment on ARM. Use the spill slot alignment as well as the local variable alignment to determine when the stack needs to be realigned. This works now that the ARM target can always realign the stack by using a base pointer. Still respect the ARMBaseRegisterInfo::canRealignStack() function vetoing a realigned stack. Don't use aligned spill code in that case. llvm-svn: 146997
2011-12-21 06:15:04 +08:00
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
target triple = "thumbv7-apple-ios"
; CHECK: f
; This function is forced to spill a double.
; Verify that the spill slot is properly aligned.
;
; The caller-saved r4 is used as a scratch register for stack realignment.
; CHECK: push {r4, r7, lr}
Fix large stack alignment codegen for ARM and Thumb2 targets This partially fixes PR13007 (ARM CodeGen fails with large stack alignment): for ARM and Thumb2 targets, but not for Thumb1, as it seems stack alignment for Thumb1 targets hasn't been supported at all. Producing an aligned stack pointer is done by zero-ing out the lower bits of the stack pointer. The BIC instruction was used for this. However, the immediate field of the BIC instruction only allows to encode an immediate that can zero out up to a maximum of the 8 lower bits. When a larger alignment is requested, a BIC instruction cannot be used; llvm was silently producing incorrect code in this case. This commit fixes code generation for large stack aligments by using the BFC instruction instead, when the BFC instruction is available. When not, it uses 2 instructions: a right shift, followed by a left shift to zero out the lower bits. The lowering of ARM::Int_eh_sjlj_dispatchsetup still has code that unconditionally uses BIC to realign the stack pointer, so it very likely has the same problem. However, I wasn't able to produce a test case for that. This commit adds an assert so that the compiler will fail the assert instead of silently generating wrong code if this is ever reached. llvm-svn: 225446
2015-01-08 23:09:14 +08:00
; CHECK: bfc r4, #0, #3
Heed spill slot alignment on ARM. Use the spill slot alignment as well as the local variable alignment to determine when the stack needs to be realigned. This works now that the ARM target can always realign the stack by using a base pointer. Still respect the ARMBaseRegisterInfo::canRealignStack() function vetoing a realigned stack. Don't use aligned spill code in that case. llvm-svn: 146997
2011-12-21 06:15:04 +08:00
; CHECK: mov sp, r4
define void @f(double* nocapture %p) nounwind ssp {
entry:
%0 = load double* %p, align 4
tail call void asm sideeffect "", "~{d8},~{d9},~{d10},~{d11},~{d12},~{d13},~{d14},~{d15}"() nounwind
tail call void @g() nounwind
store double %0, double* %p, align 4
ret void
}
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; NEON: f
; NEON: push {r4, r7, lr}
; NEON: sub.w r4, sp, #64
Fix large stack alignment codegen for ARM and Thumb2 targets This partially fixes PR13007 (ARM CodeGen fails with large stack alignment): for ARM and Thumb2 targets, but not for Thumb1, as it seems stack alignment for Thumb1 targets hasn't been supported at all. Producing an aligned stack pointer is done by zero-ing out the lower bits of the stack pointer. The BIC instruction was used for this. However, the immediate field of the BIC instruction only allows to encode an immediate that can zero out up to a maximum of the 8 lower bits. When a larger alignment is requested, a BIC instruction cannot be used; llvm was silently producing incorrect code in this case. This commit fixes code generation for large stack aligments by using the BFC instruction instead, when the BFC instruction is available. When not, it uses 2 instructions: a right shift, followed by a left shift to zero out the lower bits. The lowering of ARM::Int_eh_sjlj_dispatchsetup still has code that unconditionally uses BIC to realign the stack pointer, so it very likely has the same problem. However, I wasn't able to produce a test case for that. This commit adds an assert so that the compiler will fail the assert instead of silently generating wrong code if this is ever reached. llvm-svn: 225446
2015-01-08 23:09:14 +08:00
; NEON: bfc r4, #0, #4
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; Stack pointer must be updated before the spills.
; NEON: mov sp, r4
Make ARMAsmPrinter generate the correct alignment specifier syntax in instructions. The Printer will now print instructions with the correct alignment specifier syntax, like vld1.8 {d16}, [r0:64] llvm-svn: 175884
2013-02-22 18:01:33 +08:00
; NEON: vst1.64 {d8, d9, d10, d11}, [r4:128]!
; NEON: vst1.64 {d12, d13, d14, d15}, [r4:128]
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; Stack pointer adjustment for the stack frame contents.
; This could legally happen before the spills.
; Since the spill slot is only 8 bytes, technically it would be fine to only
; subtract #8 here. That would leave sp less aligned than some stack slots,
; and would probably blow MFI's mind.
; NEON: sub sp, #16
; The epilog is free to use another scratch register than r4.
; NEON: add r[[R4:[0-9]+]], sp, #16
Make ARMAsmPrinter generate the correct alignment specifier syntax in instructions. The Printer will now print instructions with the correct alignment specifier syntax, like vld1.8 {d16}, [r0:64] llvm-svn: 175884
2013-02-22 18:01:33 +08:00
; NEON: vld1.64 {d8, d9, d10, d11}, [r[[R4]]:128]!
; NEON: vld1.64 {d12, d13, d14, d15}, [r[[R4]]:128]
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; The stack pointer restore must happen after the reloads.
; NEON: mov sp,
; NEON: pop
Heed spill slot alignment on ARM. Use the spill slot alignment as well as the local variable alignment to determine when the stack needs to be realigned. This works now that the ARM target can always realign the stack by using a base pointer. Still respect the ARMBaseRegisterInfo::canRealignStack() function vetoing a realigned stack. Don't use aligned spill code in that case. llvm-svn: 146997
2011-12-21 06:15:04 +08:00
declare void @g()
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; Spill 7 d-registers.
define void @f7(double* nocapture %p) nounwind ssp {
entry:
tail call void asm sideeffect "", "~{d8},~{d9},~{d10},~{d11},~{d12},~{d13},~{d14}"() nounwind
ret void
}
; NEON: f7
; NEON: push {r4, r7, lr}
; NEON: sub.w r4, sp, #56
Fix large stack alignment codegen for ARM and Thumb2 targets This partially fixes PR13007 (ARM CodeGen fails with large stack alignment): for ARM and Thumb2 targets, but not for Thumb1, as it seems stack alignment for Thumb1 targets hasn't been supported at all. Producing an aligned stack pointer is done by zero-ing out the lower bits of the stack pointer. The BIC instruction was used for this. However, the immediate field of the BIC instruction only allows to encode an immediate that can zero out up to a maximum of the 8 lower bits. When a larger alignment is requested, a BIC instruction cannot be used; llvm was silently producing incorrect code in this case. This commit fixes code generation for large stack aligments by using the BFC instruction instead, when the BFC instruction is available. When not, it uses 2 instructions: a right shift, followed by a left shift to zero out the lower bits. The lowering of ARM::Int_eh_sjlj_dispatchsetup still has code that unconditionally uses BIC to realign the stack pointer, so it very likely has the same problem. However, I wasn't able to produce a test case for that. This commit adds an assert so that the compiler will fail the assert instead of silently generating wrong code if this is ever reached. llvm-svn: 225446
2015-01-08 23:09:14 +08:00
; NEON: bfc r4, #0, #4
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; Stack pointer must be updated before the spills.
; NEON: mov sp, r4
Make ARMAsmPrinter generate the correct alignment specifier syntax in instructions. The Printer will now print instructions with the correct alignment specifier syntax, like vld1.8 {d16}, [r0:64] llvm-svn: 175884
2013-02-22 18:01:33 +08:00
; NEON: vst1.64 {d8, d9, d10, d11}, [r4:128]!
; NEON: vst1.64 {d12, d13}, [r4:128]
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; NEON: vstr d14, [r4, #16]
; Epilog
; NEON: vld1.64 {d8, d9, d10, d11},
; NEON: vld1.64 {d12, d13},
; NEON: vldr d14,
; The stack pointer restore must happen after the reloads.
; NEON: mov sp,
; NEON: pop
; Spill 7 d-registers, leave a hole.
define void @f3plus4(double* nocapture %p) nounwind ssp {
entry:
tail call void asm sideeffect "", "~{d8},~{d9},~{d10},~{d12},~{d13},~{d14},~{d15}"() nounwind
ret void
}
; Aligned spilling only works for contiguous ranges starting from d8.
; The rest goes to the standard vpush instructions.
; NEON: f3plus4
; NEON: push {r4, r7, lr}
; NEON: vpush {d12, d13, d14, d15}
; NEON: sub.w r4, sp, #24
Fix large stack alignment codegen for ARM and Thumb2 targets This partially fixes PR13007 (ARM CodeGen fails with large stack alignment): for ARM and Thumb2 targets, but not for Thumb1, as it seems stack alignment for Thumb1 targets hasn't been supported at all. Producing an aligned stack pointer is done by zero-ing out the lower bits of the stack pointer. The BIC instruction was used for this. However, the immediate field of the BIC instruction only allows to encode an immediate that can zero out up to a maximum of the 8 lower bits. When a larger alignment is requested, a BIC instruction cannot be used; llvm was silently producing incorrect code in this case. This commit fixes code generation for large stack aligments by using the BFC instruction instead, when the BFC instruction is available. When not, it uses 2 instructions: a right shift, followed by a left shift to zero out the lower bits. The lowering of ARM::Int_eh_sjlj_dispatchsetup still has code that unconditionally uses BIC to realign the stack pointer, so it very likely has the same problem. However, I wasn't able to produce a test case for that. This commit adds an assert so that the compiler will fail the assert instead of silently generating wrong code if this is ever reached. llvm-svn: 225446
2015-01-08 23:09:14 +08:00
; NEON: bfc r4, #0, #4
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; Stack pointer must be updated before the spills.
; NEON: mov sp, r4
Make ARMAsmPrinter generate the correct alignment specifier syntax in instructions. The Printer will now print instructions with the correct alignment specifier syntax, like vld1.8 {d16}, [r0:64] llvm-svn: 175884
2013-02-22 18:01:33 +08:00
; NEON: vst1.64 {d8, d9}, [r4:128]
Experimental support for aligned NEON spills. ARM targets with NEON units have access to aligned vector loads and stores that are potentially faster than unaligned operations. Add support for spilling the callee-saved NEON registers to an aligned stack area using 16-byte aligned NEON loads and store. This feature is off by default, controlled by an -align-neon-spills command line option. llvm-svn: 147211
2011-12-23 08:36:18 +08:00
; NEON: vstr d10, [r4, #16]
; Epilog
; NEON: vld1.64 {d8, d9},
; NEON: vldr d10, [{{.*}}, #16]
; The stack pointer restore must happen after the reloads.
; NEON: mov sp,
; NEON: vpop {d12, d13, d14, d15}
; NEON: pop