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/imul.ll

552 lines
13 KiB
LLVM
Raw Normal View History

[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; RUN: llc < %s -mtriple=x86_64-pc-linux-gnu | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=x86_64-pc-linux-gnux32 | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=i686-pc-linux | FileCheck %s --check-prefix=X86
define i32 @mul4_32(i32 %A) {
; X64-LABEL: mul4_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: leal (,%rdi,4), %eax
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul4_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shll $2, %eax
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i32 %A, 4
ret i32 %mul
}
define i64 @mul4_64(i64 %A) {
; X64-LABEL: mul4_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: leaq (,%rdi,4), %rax
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul4_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: shldl $2, %eax, %edx
; X86-NEXT: shll $2, %eax
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i64 %A, 4
ret i64 %mul
}
define i32 @mul4096_32(i32 %A) {
; X64-LABEL: mul4096_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: shll $12, %eax
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul4096_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shll $12, %eax
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i32 %A, 4096
ret i32 %mul
}
define i64 @mul4096_64(i64 %A) {
; X64-LABEL: mul4096_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: movq %rdi, %rax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: shlq $12, %rax
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul4096_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: shldl $12, %eax, %edx
; X86-NEXT: shll $12, %eax
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i64 %A, 4096
ret i64 %mul
}
define i32 @mulmin4096_32(i32 %A) {
; X64-LABEL: mulmin4096_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: shll $12, %eax
; X64-NEXT: negl %eax
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mulmin4096_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shll $12, %eax
; X86-NEXT: negl %eax
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i32 %A, -4096
ret i32 %mul
}
define i64 @mulmin4096_64(i64 %A) {
; X64-LABEL: mulmin4096_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: movq %rdi, %rax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: shlq $12, %rax
; X64-NEXT: negq %rax
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mulmin4096_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: shldl $12, %eax, %ecx
; X86-NEXT: shll $12, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: negl %eax
; X86-NEXT: sbbl %ecx, %edx
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i64 %A, -4096
ret i64 %mul
}
define i32 @mul3_32(i32 %A) {
; X64-LABEL: mul3_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: leal (%rdi,%rdi,2), %eax
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul3_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
[X86] Form MUL_IMM for multiplies with 3/5/9 to encourage LEA formation over load folding. Previously we only formed MUL_IMM when we split a constant. This blocked load folding on those cases. We should also form MUL_IMM for 3/5/9 to favor LEA over load folding. Differential Revision: https://reviews.llvm.org/D46040 llvm-svn: 330850
2018-04-26 01:35:03 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: leal (%eax,%eax,2), %eax
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; But why?!
%mul = mul i32 %A, 3
ret i32 %mul
}
define i64 @mul3_64(i64 %A) {
; X64-LABEL: mul3_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: leaq (%rdi,%rdi,2), %rax
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul3_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
[X86] Form MUL_IMM for multiplies with 3/5/9 to encourage LEA formation over load folding. Previously we only formed MUL_IMM when we split a constant. This blocked load folding on those cases. We should also form MUL_IMM for 3/5/9 to favor LEA over load folding. Differential Revision: https://reviews.llvm.org/D46040 llvm-svn: 330850
2018-04-26 01:35:03 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: leal (%eax,%eax,2), %ecx
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86-NEXT: movl $3, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %ecx, %edx
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i64 %A, 3
ret i64 %mul
}
define i32 @mul40_32(i32 %A) {
; X64-LABEL: mul40_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: shll $3, %edi
; X64-NEXT: leal (%rdi,%rdi,4), %eax
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul40_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shll $3, %eax
; X86-NEXT: leal (%eax,%eax,4), %eax
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i32 %A, 40
ret i32 %mul
}
define i64 @mul40_64(i64 %A) {
; X64-LABEL: mul40_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: shlq $3, %rdi
; X64-NEXT: leaq (%rdi,%rdi,4), %rax
; X64-NEXT: retq
;
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
; X86-LABEL: mul40_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: leal (%eax,%eax,4), %ecx
; X86-NEXT: movl $40, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: leal (%edx,%ecx,8), %edx
; X86-NEXT: retl
[X86] Reduce some 32-bit imuls into lea + shl Reduce integer multiplication by a constant of the form k*2^c, where k is in {3,5,9} into a lea + shl. Previously it was only done for imulq on 64-bit platforms, but it makes sense for imull and 32-bit as well. Differential Revision: http://reviews.llvm.org/D7196 llvm-svn: 227308
2015-01-28 22:08:22 +08:00
%mul = mul i64 %A, 40
ret i64 %mul
}
[X86] Disable mul -> shl + lea combine when compiling for minsize Differential Revision: http://reviews.llvm.org/D11904 llvm-svn: 244740
2015-08-12 19:27:26 +08:00
define i32 @mul4_32_minsize(i32 %A) minsize {
; X64-LABEL: mul4_32_minsize:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: leal (,%rdi,4), %eax
; X64-NEXT: retq
;
[X86] Disable mul -> shl + lea combine when compiling for minsize Differential Revision: http://reviews.llvm.org/D11904 llvm-svn: 244740
2015-08-12 19:27:26 +08:00
; X86-LABEL: mul4_32_minsize:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shll $2, %eax
; X86-NEXT: retl
[X86] Disable mul -> shl + lea combine when compiling for minsize Differential Revision: http://reviews.llvm.org/D11904 llvm-svn: 244740
2015-08-12 19:27:26 +08:00
%mul = mul i32 %A, 4
ret i32 %mul
}
define i32 @mul40_32_minsize(i32 %A) minsize {
; X64-LABEL: mul40_32_minsize:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: imull $40, %edi, %eax
; X64-NEXT: retq
;
[X86] Disable mul -> shl + lea combine when compiling for minsize Differential Revision: http://reviews.llvm.org/D11904 llvm-svn: 244740
2015-08-12 19:27:26 +08:00
; X86-LABEL: mul40_32_minsize:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: imull $40, {{[0-9]+}}(%esp), %eax
; X86-NEXT: retl
[X86] Disable mul -> shl + lea combine when compiling for minsize Differential Revision: http://reviews.llvm.org/D11904 llvm-svn: 244740
2015-08-12 19:27:26 +08:00
%mul = mul i32 %A, 40
ret i32 %mul
}
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
define i32 @mul33_32(i32 %A) {
; X64-LABEL: mul33_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shll $5, %eax
; X64-NEXT: leal (%rax,%rdi), %eax
; X64-NEXT: retq
;
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
; X86-LABEL: mul33_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: shll $5, %eax
; X86-NEXT: addl %ecx, %eax
; X86-NEXT: retl
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
%mul = mul i32 %A, 33
ret i32 %mul
}
define i32 @mul31_32(i32 %A) {
; X64-LABEL: mul31_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shll $5, %eax
; X64-NEXT: subl %edi, %eax
; X64-NEXT: retq
;
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
; X86-LABEL: mul31_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: shll $5, %eax
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: retl
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
%mul = mul i32 %A, 31
ret i32 %mul
}
define i32 @mul0_32(i32 %A) {
; X64-LABEL: mul0_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: retq
;
; X86-LABEL: mul0_32:
; X86: # %bb.0:
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: retl
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
%mul = mul i32 %A, 0
ret i32 %mul
}
define i32 @mul4294967295_32(i32 %A) {
; X64-LABEL: mul4294967295_32:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: negl %eax
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64-NEXT: retq
;
; X86-LABEL: mul4294967295_32:
; X86: # %bb.0:
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: subl {{[0-9]+}}(%esp), %eax
; X86-NEXT: retl
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
%mul = mul i32 %A, 4294967295
ret i32 %mul
}
define i64 @mul18446744073709551615_64(i64 %A) {
; X64-LABEL: mul18446744073709551615_64:
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64: # %bb.0:
; X64-NEXT: movq %rdi, %rax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: negq %rax
[X86] Auto-generate complete checks. NFC llvm-svn: 330797
2018-04-25 11:40:45 +08:00
; X64-NEXT: retq
;
; X86-LABEL: mul18446744073709551615_64:
; X86: # %bb.0:
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: subl {{[0-9]+}}(%esp), %eax
; X86-NEXT: sbbl {{[0-9]+}}(%esp), %edx
; X86-NEXT: retl
[X86ISelLowering] Add additional support for multiplication-to-shift conversion. Summary: This patch adds support of conversion (mul x, 2^N + 1) => (add (shl x, N), x) and (mul x, 2^N - 1) => (sub (shl x, N), x) if the multiplication can not be converted to LEA + SHL or LEA + LEA. LLVM has already supported this on ARM, and it should also be useful on X86. Note the patch currently only applies to cases where the constant operand is positive, and I am planing to add another patch to support negative cases after this. Reviewers: craig.topper, RKSimon Subscribers: aemerson, llvm-commits Differential Revision: http://reviews.llvm.org/D14603 llvm-svn: 255415
2015-12-12 09:04:15 +08:00
%mul = mul i64 %A, 18446744073709551615
ret i64 %mul
}
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
define i32 @test(i32 %a) {
; X64-LABEL: test:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shll $5, %eax
; X64-NEXT: subl %edi, %eax
; X64-NEXT: retq
;
; X86-LABEL: test:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: shll $5, %eax
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: retl
entry:
%tmp3 = mul i32 %a, 31
ret i32 %tmp3
}
define i32 @test1(i32 %a) {
; X64-LABEL: test1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movl %edi, %eax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movl %edi, %ecx
; X64-NEXT: shll $5, %ecx
; X64-NEXT: subl %ecx, %eax
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: retq
;
; X86-LABEL: test1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] When expanding a multiply by a negative of one less than a power of 2, like 31, don't generate a negate of a subtract that we'll never optimize. We generated a subtract for the power of 2 minus one then negated the result. The negate can be optimized away by swapping the subtract operands, but DAG combine doesn't know how to do that and we don't add any of the new nodes to the worklist anyway. This patch makes use explicitly emit the swapped subtract. llvm-svn: 337858
2018-07-25 05:31:21 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: shll $5, %ecx
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: subl %ecx, %eax
; X86-NEXT: retl
entry:
%tmp3 = mul i32 %a, -31
ret i32 %tmp3
}
define i32 @test2(i32 %a) {
; X64-LABEL: test2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; X64-NEXT: # kill: def $edi killed $edi def $rdi
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shll $5, %eax
; X64-NEXT: leal (%rax,%rdi), %eax
; X64-NEXT: retq
;
; X86-LABEL: test2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: shll $5, %eax
; X86-NEXT: addl %ecx, %eax
; X86-NEXT: retl
entry:
%tmp3 = mul i32 %a, 33
ret i32 %tmp3
}
define i32 @test3(i32 %a) {
; X64-LABEL: test3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; X64-NEXT: # kill: def $edi killed $edi def $rdi
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shll $5, %eax
; X64-NEXT: leal (%rax,%rdi), %eax
; X64-NEXT: negl %eax
; X64-NEXT: retq
;
; X86-LABEL: test3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: shll $5, %eax
; X86-NEXT: addl %ecx, %eax
; X86-NEXT: negl %eax
; X86-NEXT: retl
entry:
%tmp3 = mul i32 %a, -33
ret i32 %tmp3
}
define i64 @test4(i64 %a) {
; X64-LABEL: test4:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: shlq $5, %rax
; X64-NEXT: subq %rdi, %rax
; X64-NEXT: retq
;
; X86-LABEL: test4:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: shll $5, %ecx
; X86-NEXT: subl %eax, %ecx
; X86-NEXT: movl $31, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %ecx, %edx
; X86-NEXT: retl
entry:
%tmp3 = mul i64 %a, 31
ret i64 %tmp3
}
define i64 @test5(i64 %a) {
; X64-LABEL: test5:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movq %rdi, %rax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movq %rdi, %rcx
; X64-NEXT: shlq $5, %rcx
; X64-NEXT: subq %rcx, %rax
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: retq
;
; X86-LABEL: test5:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
[X86] When expanding a multiply by a negative of one less than a power of 2, like 31, don't generate a negate of a subtract that we'll never optimize. We generated a subtract for the power of 2 minus one then negated the result. The negate can be optimized away by swapping the subtract operands, but DAG combine doesn't know how to do that and we don't add any of the new nodes to the worklist anyway. This patch makes use explicitly emit the swapped subtract. llvm-svn: 337858
2018-07-25 05:31:21 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl %esi, %eax
; X86-NEXT: shll $5, %eax
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: subl %eax, %esi
; X86-NEXT: movl $-31, %edx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %edx
; X86-NEXT: subl %ecx, %edx
[X86] When expanding a multiply by a negative of one less than a power of 2, like 31, don't generate a negate of a subtract that we'll never optimize. We generated a subtract for the power of 2 minus one then negated the result. The negate can be optimized away by swapping the subtract operands, but DAG combine doesn't know how to do that and we don't add any of the new nodes to the worklist anyway. This patch makes use explicitly emit the swapped subtract. llvm-svn: 337858
2018-07-25 05:31:21 +08:00
; X86-NEXT: addl %esi, %edx
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: popl %esi
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X86-NEXT: .cfi_def_cfa_offset 4
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: retl
entry:
%tmp3 = mul i64 %a, -31
ret i64 %tmp3
}
define i64 @test6(i64 %a) {
; X64-LABEL: test6:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: shlq $5, %rax
; X64-NEXT: leaq (%rax,%rdi), %rax
; X64-NEXT: retq
;
; X86-LABEL: test6:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: shll $5, %ecx
; X86-NEXT: addl %eax, %ecx
; X86-NEXT: movl $33, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %ecx, %edx
; X86-NEXT: retl
entry:
%tmp3 = mul i64 %a, 33
ret i64 %tmp3
}
define i64 @test7(i64 %a) {
; X64-LABEL: test7:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: shlq $5, %rax
; X64-NEXT: leaq (%rax,%rdi), %rax
; X64-NEXT: negq %rax
; X64-NEXT: retq
;
; X86-LABEL: test7:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: pushl %esi
[X86] Correct dwarf unwind information in function epilogue CFI instructions that set appropriate cfa offset and cfa register are now inserted in emitEpilogue() in X86FrameLowering. Majority of the changes in this patch: 1. Ensure that CFI instructions do not affect code generation. 2. Enable maintaining correct information about cfa offset and cfa register in a function when basic blocks are reordered, merged, split, duplicated. These changes are target independent and described below. Changed CFI instructions so that they: 1. are duplicable 2. are not counted as instructions when tail duplicating or tail merging 3. can be compared as equal Add information to each MachineBasicBlock about cfa offset and cfa register that are valid at its entry and exit (incoming and outgoing CFI info). Add support for updating this information when basic blocks are merged, split, duplicated, created. Add a verification pass (CFIInfoVerifier) that checks that outgoing cfa offset and register of predecessor blocks match incoming values of their successors. Incoming and outgoing CFI information is used by a late pass (CFIInstrInserter) that corrects CFA calculation rule for a basic block if needed. That means that additional CFI instructions get inserted at basic block beginning to correct the rule for calculating CFA. Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D18046 llvm-svn: 306529
2017-06-28 18:21:17 +08:00
; X86-NEXT: .cfi_def_cfa_offset 8
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl %eax, %esi
; X86-NEXT: shll $5, %esi
; X86-NEXT: addl %eax, %esi
; X86-NEXT: movl $-33, %edx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %edx
; X86-NEXT: subl %ecx, %edx
; X86-NEXT: subl %esi, %edx
; X86-NEXT: popl %esi
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X86-NEXT: .cfi_def_cfa_offset 4
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: retl
entry:
%tmp3 = mul i64 %a, -33
ret i64 %tmp3
}
define i64 @testOverflow(i64 %a) {
; X64-LABEL: testOverflow:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0: # %entry
[X86] Remove an unnecessary 'if' that prevented treating INT64_MAX and -INT64_MAX as power of 2 minus 1 in the multiply expansion code. Not sure why they were being explicitly excluded, but I believe all the math inside the if works. I changed the absolute value to be uint64_t instead of int64_t so INT64_MIN+1 wouldn't be signed wrap. llvm-svn: 338101
2018-07-27 13:56:27 +08:00
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: shlq $63, %rax
; X64-NEXT: subq %rdi, %rax
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X64-NEXT: retq
;
; X86-LABEL: testOverflow:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X86: # %bb.0: # %entry
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: .cfi_offset %esi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl $-1, %edx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %edx
; X86-NEXT: movl %ecx, %esi
; X86-NEXT: shll $31, %esi
; X86-NEXT: subl %ecx, %esi
; X86-NEXT: addl %esi, %edx
; X86-NEXT: subl {{[0-9]+}}(%esp), %edx
; X86-NEXT: popl %esi
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X86-NEXT: .cfi_def_cfa_offset 4
[X86] Improve mul combine for negative multiplayer (2^c - 1) This patch improves the mul instruction combine function (combineMul) by adding new layer of logic. In this patch, we are adding the ability to fold (mul x, -((1 << c) -1)) or (mul x, -((1 << c) +1)) into (neg(X << c) -x) or (neg((x << c) + x) respective. Differential Revision: https://reviews.llvm.org/D28232 llvm-svn: 292358
2017-01-18 17:31:13 +08:00
; X86-NEXT: retl
entry:
%tmp3 = mul i64 %a, 9223372036854775807
ret i64 %tmp3
}
[X86] Remove an unnecessary 'if' that prevented treating INT64_MAX and -INT64_MAX as power of 2 minus 1 in the multiply expansion code. Not sure why they were being explicitly excluded, but I believe all the math inside the if works. I changed the absolute value to be uint64_t instead of int64_t so INT64_MIN+1 wouldn't be signed wrap. llvm-svn: 338101
2018-07-27 13:56:27 +08:00
define i64 @testNegOverflow(i64 %a) {
; X64-LABEL: testNegOverflow:
; X64: # %bb.0: # %entry
; X64-NEXT: movq %rdi, %rax
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movq %rdi, %rcx
; X64-NEXT: shlq $63, %rcx
; X64-NEXT: subq %rcx, %rax
[X86] Remove an unnecessary 'if' that prevented treating INT64_MAX and -INT64_MAX as power of 2 minus 1 in the multiply expansion code. Not sure why they were being explicitly excluded, but I believe all the math inside the if works. I changed the absolute value to be uint64_t instead of int64_t so INT64_MIN+1 wouldn't be signed wrap. llvm-svn: 338101
2018-07-27 13:56:27 +08:00
; X64-NEXT: retq
;
; X86-LABEL: testNegOverflow:
; X86: # %bb.0: # %entry
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl $1, %edx
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %edx
; X86-NEXT: shll $31, %ecx
; X86-NEXT: addl %ecx, %edx
; X86-NEXT: addl {{[0-9]+}}(%esp), %edx
; X86-NEXT: retl
entry:
%tmp3 = mul i64 %a, -9223372036854775807
ret i64 %tmp3
}