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/vectorcall.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

224 lines
7.8 KiB
LLVM
Raw Normal View History

X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
; RUN: llc -mtriple=i686-pc-win32 -mattr=+sse2 < %s | FileCheck %s --check-prefix=CHECK --check-prefix=X86
; RUN: llc -mtriple=x86_64-pc-win32 < %s | FileCheck %s --check-prefix=CHECK --check-prefix=X64
; Test integer arguments.
define x86_vectorcallcc i32 @test_int_1() {
; CHECK-LABEL: {{^}}test_int_1@@0:
; CHECK: xorl %eax, %eax
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret i32 0
}
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
define x86_vectorcallcc i32 @test_int_2(i32 inreg %a) {
; X86-LABEL: {{^}}test_int_2@@4:
; X64-LABEL: {{^}}test_int_2@@8:
; CHECK: movl %ecx, %eax
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret i32 %a
}
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
define x86_vectorcallcc i32 @test_int_3(i64 inreg %a) {
; X86-LABEL: {{^}}test_int_3@@8:
; X64-LABEL: {{^}}test_int_3@@8:
[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
; X86: movl %ecx, %eax
; X64: movq %rcx, %rax
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
%at = trunc i64 %a to i32
ret i32 %at
}
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
define x86_vectorcallcc i32 @test_int_4(i32 inreg %a, i32 inreg %b) {
; X86-LABEL: {{^}}test_int_4@@8:
; X86: leal (%ecx,%edx), %eax
; X64-LABEL: {{^}}test_int_4@@16:
; X64: leal (%rcx,%rdx), %eax
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
%s = add i32 %a, %b
ret i32 %s
}
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
define x86_vectorcallcc i32 @"\01test_int_5"(i32, i32) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: {{^}}test_int_5:
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
ret i32 0
}
define x86_vectorcallcc double @test_fp_1(double %a, double %b) {
; CHECK-LABEL: {{^}}test_fp_1@@16:
; CHECK: movaps %xmm1, %xmm0
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret double %b
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
}
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
define x86_vectorcallcc double @test_fp_2(double, double, double, double, double, double, double %r) {
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
; CHECK-LABEL: {{^}}test_fp_2@@56:
; CHECK: movsd {{[0-9]+\(%[re]sp\)}}, %xmm0
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret double %r
}
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
define x86_vectorcallcc {double, double, double, double} @test_fp_3() {
; CHECK-LABEL: {{^}}test_fp_3@@0:
; CHECK: xorps %xmm0
; CHECK: xorps %xmm1
; CHECK: xorps %xmm2
; CHECK: xorps %xmm3
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret {double, double, double, double}
{ double 0.0, double 0.0, double 0.0, double 0.0 }
}
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
; FIXME: Returning via x87 isn't compatible, but its hard to structure the
; tablegen any other way.
define x86_vectorcallcc {double, double, double, double, double} @test_fp_4() {
; CHECK-LABEL: {{^}}test_fp_4@@0:
; CHECK: fldz
; CHECK: xorps %xmm0
; CHECK: xorps %xmm1
; CHECK: xorps %xmm2
; CHECK: xorps %xmm3
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret {double, double, double, double, double}
{ double 0.0, double 0.0, double 0.0, double 0.0, double 0.0 }
}
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
define x86_vectorcallcc <16 x i8> @test_vec_1(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: {{^}}test_vec_1@@32:
; CHECK: movaps %xmm1, %xmm0
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret <16 x i8> %b
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
}
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
define x86_vectorcallcc <16 x i8> @test_vec_2(double, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> %r) {
X86: Implement the vectorcall calling convention This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 llvm-svn: 220745
2014-10-28 09:29:26 +08:00
; CHECK-LABEL: {{^}}test_vec_2@@104:
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; X64: movq {{[0-9]*}}(%rsp), %rax
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
; CHECK: movaps (%{{rax|ecx}}), %xmm0
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
ret <16 x i8> %r
}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
%struct.HVA5 = type { <4 x float>, <4 x float>, <4 x float>, <4 x float>, <4 x float> }
%struct.HVA4 = type { <4 x float>, <4 x float>, <4 x float>, <4 x float> }
%struct.HVA3 = type { <4 x float>, <4 x float>, <4 x float> }
%struct.HVA2 = type { <4 x float>, <4 x float> }
define x86_vectorcallcc <4 x float> @test_mixed_1(i32 %a, %struct.HVA4 inreg %bb, i32 %c) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: test_mixed_1
; CHECK: movaps %xmm1, 16(%{{(e|r)}}sp)
; CHECK: movaps %xmm1, %xmm0
; CHECK: ret{{q|l}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%b = alloca %struct.HVA4, align 16
store %struct.HVA4 %bb, %struct.HVA4* %b, align 16
%w1 = getelementptr inbounds %struct.HVA4, %struct.HVA4* %b, i32 0, i32 1
%0 = load <4 x float>, <4 x float>* %w1, align 16
ret <4 x float> %0
}
define x86_vectorcallcc <4 x float> @test_mixed_2(%struct.HVA4 inreg %a, %struct.HVA4* %b, <4 x float> %c) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: test_mixed_2
; X86: movaps %xmm0, (%esp)
; X64: movaps %xmm2, %xmm0
; CHECK: ret{{[ql]}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%c.addr = alloca <4 x float>, align 16
store <4 x float> %c, <4 x float>* %c.addr, align 16
%0 = load <4 x float>, <4 x float>* %c.addr, align 16
ret <4 x float> %0
}
define x86_vectorcallcc <4 x float> @test_mixed_3(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, <4 x float> %e, %struct.HVA2* %f) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: test_mixed_3
; CHECK: movaps (%{{[re][ac]}}x), %xmm0
; CHECK: ret{{[ql]}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%x = getelementptr inbounds %struct.HVA2, %struct.HVA2* %f, i32 0, i32 0
%0 = load <4 x float>, <4 x float>* %x, align 16
ret <4 x float> %0
}
define x86_vectorcallcc <4 x float> @test_mixed_4(%struct.HVA4 inreg %a, %struct.HVA2* %bb, <4 x float> %c) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: test_mixed_4
; X86: movaps 16(%eax), %xmm0
; X64: movaps 16(%rdx), %xmm0
; CHECK: ret{{[ql]}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%y4 = getelementptr inbounds %struct.HVA2, %struct.HVA2* %bb, i32 0, i32 1
%0 = load <4 x float>, <4 x float>* %y4, align 16
ret <4 x float> %0
}
define x86_vectorcallcc <4 x float> @test_mixed_5(%struct.HVA3 inreg %a, %struct.HVA3* %b, <4 x float> %c, %struct.HVA2 inreg %dd) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: test_mixed_5
; CHECK-DAG: movaps %xmm{{[0,5]}}, 16(%{{(e|r)}}sp)
; CHECK-DAG: movaps %xmm5, %xmm0
; CHECK: ret{{[ql]}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%d = alloca %struct.HVA2, align 16
store %struct.HVA2 %dd, %struct.HVA2* %d, align 16
%y5 = getelementptr inbounds %struct.HVA2, %struct.HVA2* %d, i32 0, i32 1
%0 = load <4 x float>, <4 x float>* %y5, align 16
ret <4 x float> %0
}
define x86_vectorcallcc %struct.HVA4 @test_mixed_6(%struct.HVA4 inreg %a, %struct.HVA4* %b) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: test_mixed_6
; CHECK: movaps (%{{[re]}}sp), %xmm0
; CHECK: movaps 16(%{{[re]}}sp), %xmm1
; CHECK: movaps 32(%{{[re]}}sp), %xmm2
; CHECK: movaps 48(%{{[re]}}sp), %xmm3
; CHECK: ret{{[ql]}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%retval = alloca %struct.HVA4, align 16
%0 = bitcast %struct.HVA4* %retval to i8*
%1 = bitcast %struct.HVA4* %b to i8*
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-20 01:13:12 +08:00
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %0, i8* align 16 %1, i32 64, i1 false)
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
%2 = load %struct.HVA4, %struct.HVA4* %retval, align 16
ret %struct.HVA4 %2
}
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-20 01:13:12 +08:00
declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1)
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1)
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1)
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
OpaquePtr: Bulk update tests to use typed sret
2020-11-21 03:07:11 +08:00
define x86_vectorcallcc void @test_mixed_7(%struct.HVA5* noalias sret(%struct.HVA5) %agg.result) {
OpaquePtr: Add helpers for sret to mirror byval Sret should really have a type parameter like byval does.
2020-09-23 23:03:38 +08:00
; X86-LABEL: test_mixed_7@@4
; X64-LABEL: test_mixed_7@@8
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; X64: mov{{[ql]}} %rcx, %rax
; CHECK: movaps %xmm{{[0-9]}}, 64(%{{rcx|eax}})
; CHECK: movaps %xmm{{[0-9]}}, 48(%{{rcx|eax}})
; CHECK: movaps %xmm{{[0-9]}}, 32(%{{rcx|eax}})
; CHECK: movaps %xmm{{[0-9]}}, 16(%{{rcx|eax}})
; CHECK: movaps %xmm{{[0-9]}}, (%{{rcx|eax}})
; CHECK: ret{{[ql]}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%a = alloca %struct.HVA5, align 16
%0 = bitcast %struct.HVA5* %a to i8*
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-20 01:13:12 +08:00
call void @llvm.memset.p0i8.i64(i8* align 16 %0, i8 0, i64 80, i1 false)
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
%1 = bitcast %struct.HVA5* %agg.result to i8*
%2 = bitcast %struct.HVA5* %a to i8*
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-20 01:13:12 +08:00
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %1, i8* align 16 %2, i64 80, i1 false)
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
ret void
}
define x86_vectorcallcc <4 x float> @test_mixed_8(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, i32 %e, <4 x float> %f) {
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
; CHECK-LABEL: test_mixed_8
; X86: movaps %xmm4, %xmm0
; X64: movaps %xmm5, %xmm0
; CHECK: ret{{[ql]}}
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
entry:
%f.addr = alloca <4 x float>, align 16
store <4 x float> %f, <4 x float>* %f.addr, align 16
%0 = load <4 x float>, <4 x float>* %f.addr, align 16
ret <4 x float> %0
}
%struct.HFA4 = type { double, double, double, double }
declare x86_vectorcallcc double @test_mixed_9_callee(%struct.HFA4 %x, double %y)
define x86_vectorcallcc double @test_mixed_9_caller(%struct.HFA4 inreg %b) {
; CHECK-LABEL: test_mixed_9_caller
; CHECK: movaps %xmm3, %xmm4
; CHECK: movaps %xmm2, %xmm3
; CHECK: movaps %xmm1, %xmm2
; X32: movasd %xmm0, %xmm1
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support Fixing failing test. llvm-svn: 290246
2016-12-21 17:18:37 +08:00
; X64: movap{{d|s}} %xmm5, %xmm1
[X86] Vectorcall Calling Convention - Adding CodeGen Complete Support The vectorcall calling convention specifies that arguments to functions are to be passed in registers, when possible. vectorcall uses more registers for arguments than fastcall or the default x64 calling convention use. The vectorcall calling convention is only supported in native code on x86 and x64 processors that include Streaming SIMD Extensions 2 (SSE2) and above. The current implementation does not handle Homogeneous Vector Aggregates (HVAs) correctly and this review attempts to fix it. This aubmit also includes additional lit tests to cover better HVAs corner cases. Differential Revision: https://reviews.llvm.org/D27392 llvm-svn: 290240
2016-12-21 16:31:45 +08:00
; CHECK: call{{l|q}} test_mixed_9_callee@@40
; CHECK: addsd {{.*}}, %xmm0
; CHECK: ret{{l|q}}
[X86] Cleanup vectorcall test checks PR32397 still needs to be fixed for the update script to process this
2020-04-05 03:13:54 +08:00
entry:
%call = call x86_vectorcallcc double @test_mixed_9_callee(%struct.HFA4 inreg %b, double 3.000000e+00)
%add = fadd double 1.000000e+00, %call
ret double %add
}