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/min-legal-vector-width.ll

649 lines
32 KiB
LLVM
Raw Normal View History

[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512vl,avx512bw,avx512dq,prefer-256-bit | FileCheck %s
; This file primarily contains tests for specific places in X86ISelLowering.cpp that needed be made aware of the legalizer not allowing 512-bit vectors due to prefer-256-bit even though AVX512 is enabled.
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @add256(<16 x i32>* %a, <16 x i32>* %b, <16 x i32>* %c) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: add256:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa (%rdi), %ymm0
; CHECK-NEXT: vmovdqa 32(%rdi), %ymm1
; CHECK-NEXT: vpaddd (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vpaddd 32(%rsi), %ymm1, %ymm1
; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
; CHECK-NEXT: vmovdqa %ymm0, (%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%d = load <16 x i32>, <16 x i32>* %a
%e = load <16 x i32>, <16 x i32>* %b
%f = add <16 x i32> %d, %e
store <16 x i32> %f, <16 x i32>* %c
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @add512(<16 x i32>* %a, <16 x i32>* %b, <16 x i32>* %c) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: add512:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa64 (%rdi), %zmm0
; CHECK-NEXT: vpaddd (%rsi), %zmm0, %zmm0
; CHECK-NEXT: vmovdqa64 %zmm0, (%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%d = load <16 x i32>, <16 x i32>* %a
%e = load <16 x i32>, <16 x i32>* %b
%f = add <16 x i32> %d, %e
store <16 x i32> %f, <16 x i32>* %c
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @avg_v64i8_256(<64 x i8>* %a, <64 x i8>* %b) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: avg_v64i8_256:
; CHECK: # %bb.0:
[DAG, X86] Revert r327197 "Revert r327170, r327171, r327172" Reland ISel cycle checking improvements after simplifying node id invariant traversal and correcting typo. llvm-svn: 327898
2018-03-20 04:19:46 +08:00
; CHECK-NEXT: vmovdqa (%rsi), %ymm0
; CHECK-NEXT: vmovdqa 32(%rsi), %ymm1
; CHECK-NEXT: vpavgb (%rdi), %ymm0, %ymm0
; CHECK-NEXT: vpavgb 32(%rdi), %ymm1, %ymm1
Revert "[DAG, X86] Revert r327197 "Revert r327170, r327171, r327172"" as it times out building test-suite on PPC. llvm-svn: 327778
2018-03-18 03:24:54 +08:00
; CHECK-NEXT: vmovdqu %ymm1, (%rax)
[DAG, X86] Revert r327197 "Revert r327170, r327171, r327172" Reland ISel cycle checking improvements after simplifying node id invariant traversal and correcting typo. llvm-svn: 327898
2018-03-20 04:19:46 +08:00
; CHECK-NEXT: vmovdqu %ymm0, (%rax)
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%1 = load <64 x i8>, <64 x i8>* %a
%2 = load <64 x i8>, <64 x i8>* %b
%3 = zext <64 x i8> %1 to <64 x i32>
%4 = zext <64 x i8> %2 to <64 x i32>
%5 = add nuw nsw <64 x i32> %3, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%6 = add nuw nsw <64 x i32> %5, %4
%7 = lshr <64 x i32> %6, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%8 = trunc <64 x i32> %7 to <64 x i8>
store <64 x i8> %8, <64 x i8>* undef, align 4
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @avg_v64i8_512(<64 x i8>* %a, <64 x i8>* %b) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: avg_v64i8_512:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa64 (%rsi), %zmm0
; CHECK-NEXT: vpavgb (%rdi), %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, (%rax)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%1 = load <64 x i8>, <64 x i8>* %a
%2 = load <64 x i8>, <64 x i8>* %b
%3 = zext <64 x i8> %1 to <64 x i32>
%4 = zext <64 x i8> %2 to <64 x i32>
%5 = add nuw nsw <64 x i32> %3, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%6 = add nuw nsw <64 x i32> %5, %4
%7 = lshr <64 x i32> %6, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%8 = trunc <64 x i32> %7 to <64 x i8>
store <64 x i8> %8, <64 x i8>* undef, align 4
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @pmaddwd_32_256(<32 x i16>* %APtr, <32 x i16>* %BPtr, <16 x i32>* %CPtr) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: pmaddwd_32_256:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa (%rdi), %ymm0
; CHECK-NEXT: vmovdqa 32(%rdi), %ymm1
; CHECK-NEXT: vpmaddwd (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vpmaddwd 32(%rsi), %ymm1, %ymm1
; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
; CHECK-NEXT: vmovdqa %ymm0, (%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%A = load <32 x i16>, <32 x i16>* %APtr
%B = load <32 x i16>, <32 x i16>* %BPtr
%a = sext <32 x i16> %A to <32 x i32>
%b = sext <32 x i16> %B to <32 x i32>
%m = mul nsw <32 x i32> %a, %b
%odd = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
%even = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
%ret = add <16 x i32> %odd, %even
store <16 x i32> %ret, <16 x i32>* %CPtr
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @pmaddwd_32_512(<32 x i16>* %APtr, <32 x i16>* %BPtr, <16 x i32>* %CPtr) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: pmaddwd_32_512:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa64 (%rdi), %zmm0
; CHECK-NEXT: vpmaddwd (%rsi), %zmm0, %zmm0
; CHECK-NEXT: vmovdqa64 %zmm0, (%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%A = load <32 x i16>, <32 x i16>* %APtr
%B = load <32 x i16>, <32 x i16>* %BPtr
%a = sext <32 x i16> %A to <32 x i32>
%b = sext <32 x i16> %B to <32 x i32>
%m = mul nsw <32 x i32> %a, %b
%odd = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
%even = shufflevector <32 x i32> %m, <32 x i32> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
%ret = add <16 x i32> %odd, %even
store <16 x i32> %ret, <16 x i32>* %CPtr
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @psubus_64i8_max_256(<64 x i8>* %xptr, <64 x i8>* %yptr, <64 x i8>* %zptr) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: psubus_64i8_max_256:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa (%rdi), %ymm0
; CHECK-NEXT: vmovdqa 32(%rdi), %ymm1
; CHECK-NEXT: vpsubusb (%rsi), %ymm0, %ymm0
; CHECK-NEXT: vpsubusb 32(%rsi), %ymm1, %ymm1
; CHECK-NEXT: vmovdqa %ymm1, 32(%rdx)
; CHECK-NEXT: vmovdqa %ymm0, (%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%x = load <64 x i8>, <64 x i8>* %xptr
%y = load <64 x i8>, <64 x i8>* %yptr
%cmp = icmp ult <64 x i8> %x, %y
%max = select <64 x i1> %cmp, <64 x i8> %y, <64 x i8> %x
%res = sub <64 x i8> %max, %y
store <64 x i8> %res, <64 x i8>* %zptr
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @psubus_64i8_max_512(<64 x i8>* %xptr, <64 x i8>* %yptr, <64 x i8>* %zptr) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: psubus_64i8_max_512:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovdqa64 (%rdi), %zmm0
; CHECK-NEXT: vpsubusb (%rsi), %zmm0, %zmm0
; CHECK-NEXT: vmovdqa64 %zmm0, (%rdx)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%x = load <64 x i8>, <64 x i8>* %xptr
%y = load <64 x i8>, <64 x i8>* %yptr
%cmp = icmp ult <64 x i8> %x, %y
%max = select <64 x i1> %cmp, <64 x i8> %y, <64 x i8> %x
%res = sub <64 x i8> %max, %y
store <64 x i8> %res, <64 x i8>* %zptr
ret void
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define i32 @_Z9test_charPcS_i_256(i8* nocapture readonly, i8* nocapture readonly, i32) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: _Z9test_charPcS_i_256:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: vpxor %xmm0, %xmm0, %xmm0
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB8_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
[X86] Remove the max vector width restriction from combineLoopMAddPattern and rely splitOpsAndApply to handle splitting. This seems to be a net improvement. There's still an issue under avx512f where we have a 512-bit vpaddd, but not vpmaddwd so we end up doing two 256-bit vpmaddwds and inserting the results before a 512-bit vpaddd. It might be better to do two 512-bits paddds with zeros in the upper half. Same number of instructions, but breaks a dependency. llvm-svn: 337656
2018-07-23 03:44:35 +08:00
; CHECK-NEXT: vpmovsxbw (%rdi,%rcx), %ymm3
; CHECK-NEXT: vpmovsxbw 16(%rdi,%rcx), %ymm4
; CHECK-NEXT: vpmovsxbw (%rsi,%rcx), %ymm5
; CHECK-NEXT: vpmaddwd %ymm3, %ymm5, %ymm3
; CHECK-NEXT: vpaddd %ymm1, %ymm3, %ymm1
; CHECK-NEXT: vpmovsxbw 16(%rsi,%rcx), %ymm3
; CHECK-NEXT: vpmaddwd %ymm4, %ymm3, %ymm3
; CHECK-NEXT: vpaddd %ymm2, %ymm3, %ymm2
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: addq $32, %rcx
; CHECK-NEXT: cmpq %rcx, %rax
; CHECK-NEXT: jne .LBB8_1
; CHECK-NEXT: # %bb.2: # %middle.block
[X86] Remove the max vector width restriction from combineLoopMAddPattern and rely splitOpsAndApply to handle splitting. This seems to be a net improvement. There's still an issue under avx512f where we have a 512-bit vpaddd, but not vpmaddwd so we end up doing two 256-bit vpmaddwds and inserting the results before a 512-bit vpaddd. It might be better to do two 512-bits paddds with zeros in the upper half. Same number of instructions, but breaks a dependency. llvm-svn: 337656
2018-07-23 03:44:35 +08:00
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm1
; CHECK-NEXT: vpaddd %ymm0, %ymm2, %ymm0
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vextracti128 $1, %ymm0, %xmm1
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0
[x86] add and use fast horizontal vector math subtarget feature This is the planned follow-up to D52997. Here we are reducing horizontal vector math codegen by default. AMD Jaguar (btver2) should have no difference with this patch because it has fast-hops. (If we want to set that bit for other CPUs, let me know.) The code changes are small, but there are many test diffs. For files that are specifically testing for hops, I added RUNs to distinguish fast/slow, so we can see the consequences side-by-side. For files that are primarily concerned with codegen other than hops, I just updated the CHECK lines to reflect the new default codegen. To recap the recent horizontal op story: 1. Before rL343727, we were producing hops for all subtargets for a variety of patterns. Hops were likely not optimal for all targets though. 2. The IR improvement in r343727 exposed a hole in the backend hop pattern matching, so we reduced hop codegen for all subtargets. That was bad for Jaguar (PR39195). 3. We restored the hop codegen for all targets with rL344141. Good for Jaguar, but probably bad for other CPUs. 4. This patch allows us to distinguish when we want to produce hops, so everyone can be happy. I'm not sure if we have the best predicate here, but the intent is to undo the extra hop-iness that was enabled by r344141. Differential Revision: https://reviews.llvm.org/D53095 llvm-svn: 344361
2018-10-13 00:41:02 +08:00
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
[DAGCombiner] narrow vector binops when extraction is cheap Narrowing vector binops came up in the demanded bits discussion in D52912. I don't think we're going to be able to do this transform in IR as a canonicalization because of the risk of creating unsupported widths for vector ops, but we already have a DAG TLI hook to allow what I was hoping for: isExtractSubvectorCheap(). This is currently enabled for x86, ARM, and AArch64 (although only x86 has existing regression test diffs). This is artificially limited to not look through bitcasts because there are so many test diffs already, but that's marked with a TODO and is a small follow-up. Differential Revision: https://reviews.llvm.org/D53784 llvm-svn: 345602
2018-10-30 22:14:34 +08:00
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vmovd %xmm0, %eax
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
%3 = zext i32 %2 to i64
br label %vector.body
vector.body:
%index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
%vec.phi = phi <32 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
%4 = getelementptr inbounds i8, i8* %0, i64 %index
%5 = bitcast i8* %4 to <32 x i8>*
%wide.load = load <32 x i8>, <32 x i8>* %5, align 1
%6 = sext <32 x i8> %wide.load to <32 x i32>
%7 = getelementptr inbounds i8, i8* %1, i64 %index
%8 = bitcast i8* %7 to <32 x i8>*
%wide.load14 = load <32 x i8>, <32 x i8>* %8, align 1
%9 = sext <32 x i8> %wide.load14 to <32 x i32>
%10 = mul nsw <32 x i32> %9, %6
%11 = add nsw <32 x i32> %10, %vec.phi
%index.next = add i64 %index, 32
%12 = icmp eq i64 %index.next, %3
br i1 %12, label %middle.block, label %vector.body
middle.block:
%rdx.shuf1 = shufflevector <32 x i32> %11, <32 x i32> undef, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx1 = add <32 x i32> %11, %rdx.shuf1
%rdx.shuf = shufflevector <32 x i32> %bin.rdx1, <32 x i32> undef, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx = add <32 x i32> %bin.rdx1, %rdx.shuf
%rdx.shuf15 = shufflevector <32 x i32> %bin.rdx, <32 x i32> undef, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx32 = add <32 x i32> %bin.rdx, %rdx.shuf15
%rdx.shuf17 = shufflevector <32 x i32> %bin.rdx32, <32 x i32> undef, <32 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx18 = add <32 x i32> %bin.rdx32, %rdx.shuf17
%rdx.shuf19 = shufflevector <32 x i32> %bin.rdx18, <32 x i32> undef, <32 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx20 = add <32 x i32> %bin.rdx18, %rdx.shuf19
%13 = extractelement <32 x i32> %bin.rdx20, i32 0
ret i32 %13
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define i32 @_Z9test_charPcS_i_512(i8* nocapture readonly, i8* nocapture readonly, i32) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: _Z9test_charPcS_i_512:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: vpxor %xmm0, %xmm0, %xmm0
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB9_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vpmovsxbw (%rdi,%rcx), %zmm2
; CHECK-NEXT: vpmovsxbw (%rsi,%rcx), %zmm3
; CHECK-NEXT: vpmaddwd %zmm2, %zmm3, %zmm2
; CHECK-NEXT: vpaddd %zmm1, %zmm2, %zmm1
; CHECK-NEXT: addq $32, %rcx
; CHECK-NEXT: cmpq %rcx, %rax
; CHECK-NEXT: jne .LBB9_1
; CHECK-NEXT: # %bb.2: # %middle.block
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
; CHECK-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vextracti128 $1, %ymm0, %xmm1
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
[DAGCombiner] narrow vector binops when extraction is cheap Narrowing vector binops came up in the demanded bits discussion in D52912. I don't think we're going to be able to do this transform in IR as a canonicalization because of the risk of creating unsupported widths for vector ops, but we already have a DAG TLI hook to allow what I was hoping for: isExtractSubvectorCheap(). This is currently enabled for x86, ARM, and AArch64 (although only x86 has existing regression test diffs). This is artificially limited to not look through bitcasts because there are so many test diffs already, but that's marked with a TODO and is a small follow-up. Differential Revision: https://reviews.llvm.org/D53784 llvm-svn: 345602
2018-10-30 22:14:34 +08:00
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vmovd %xmm0, %eax
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
%3 = zext i32 %2 to i64
br label %vector.body
vector.body:
%index = phi i64 [ %index.next, %vector.body ], [ 0, %entry ]
%vec.phi = phi <32 x i32> [ %11, %vector.body ], [ zeroinitializer, %entry ]
%4 = getelementptr inbounds i8, i8* %0, i64 %index
%5 = bitcast i8* %4 to <32 x i8>*
%wide.load = load <32 x i8>, <32 x i8>* %5, align 1
%6 = sext <32 x i8> %wide.load to <32 x i32>
%7 = getelementptr inbounds i8, i8* %1, i64 %index
%8 = bitcast i8* %7 to <32 x i8>*
%wide.load14 = load <32 x i8>, <32 x i8>* %8, align 1
%9 = sext <32 x i8> %wide.load14 to <32 x i32>
%10 = mul nsw <32 x i32> %9, %6
%11 = add nsw <32 x i32> %10, %vec.phi
%index.next = add i64 %index, 32
%12 = icmp eq i64 %index.next, %3
br i1 %12, label %middle.block, label %vector.body
middle.block:
%rdx.shuf1 = shufflevector <32 x i32> %11, <32 x i32> undef, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx1 = add <32 x i32> %11, %rdx.shuf1
%rdx.shuf = shufflevector <32 x i32> %bin.rdx1, <32 x i32> undef, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx = add <32 x i32> %bin.rdx1, %rdx.shuf
%rdx.shuf15 = shufflevector <32 x i32> %bin.rdx, <32 x i32> undef, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx32 = add <32 x i32> %bin.rdx, %rdx.shuf15
%rdx.shuf17 = shufflevector <32 x i32> %bin.rdx32, <32 x i32> undef, <32 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx18 = add <32 x i32> %bin.rdx32, %rdx.shuf17
%rdx.shuf19 = shufflevector <32 x i32> %bin.rdx18, <32 x i32> undef, <32 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx20 = add <32 x i32> %bin.rdx18, %rdx.shuf19
%13 = extractelement <32 x i32> %bin.rdx20, i32 0
ret i32 %13
}
@a = global [1024 x i8] zeroinitializer, align 16
@b = global [1024 x i8] zeroinitializer, align 16
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define i32 @sad_16i8_256() "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: sad_16i8_256:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vpxor %xmm0, %xmm0, %xmm0
; CHECK-NEXT: movq $-1024, %rax # imm = 0xFC00
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB10_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vmovdqu a+1024(%rax), %xmm2
; CHECK-NEXT: vpsadbw b+1024(%rax), %xmm2, %xmm2
; CHECK-NEXT: vpaddd %ymm1, %ymm2, %ymm1
; CHECK-NEXT: addq $4, %rax
; CHECK-NEXT: jne .LBB10_1
; CHECK-NEXT: # %bb.2: # %middle.block
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: vextracti128 $1, %ymm0, %xmm1
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0
[x86] add and use fast horizontal vector math subtarget feature This is the planned follow-up to D52997. Here we are reducing horizontal vector math codegen by default. AMD Jaguar (btver2) should have no difference with this patch because it has fast-hops. (If we want to set that bit for other CPUs, let me know.) The code changes are small, but there are many test diffs. For files that are specifically testing for hops, I added RUNs to distinguish fast/slow, so we can see the consequences side-by-side. For files that are primarily concerned with codegen other than hops, I just updated the CHECK lines to reflect the new default codegen. To recap the recent horizontal op story: 1. Before rL343727, we were producing hops for all subtargets for a variety of patterns. Hops were likely not optimal for all targets though. 2. The IR improvement in r343727 exposed a hole in the backend hop pattern matching, so we reduced hop codegen for all subtargets. That was bad for Jaguar (PR39195). 3. We restored the hop codegen for all targets with rL344141. Good for Jaguar, but probably bad for other CPUs. 4. This patch allows us to distinguish when we want to produce hops, so everyone can be happy. I'm not sure if we have the best predicate here, but the intent is to undo the extra hop-iness that was enabled by r344141. Differential Revision: https://reviews.llvm.org/D53095 llvm-svn: 344361
2018-10-13 00:41:02 +08:00
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
[DAGCombiner] narrow vector binops when extraction is cheap Narrowing vector binops came up in the demanded bits discussion in D52912. I don't think we're going to be able to do this transform in IR as a canonicalization because of the risk of creating unsupported widths for vector ops, but we already have a DAG TLI hook to allow what I was hoping for: isExtractSubvectorCheap(). This is currently enabled for x86, ARM, and AArch64 (although only x86 has existing regression test diffs). This is artificially limited to not look through bitcasts because there are so many test diffs already, but that's marked with a TODO and is a small follow-up. Differential Revision: https://reviews.llvm.org/D53784 llvm-svn: 345602
2018-10-30 22:14:34 +08:00
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vmovd %xmm0, %eax
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
br label %vector.body
vector.body:
%index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
%vec.phi = phi <16 x i32> [ zeroinitializer, %entry ], [ %10, %vector.body ]
%0 = getelementptr inbounds [1024 x i8], [1024 x i8]* @a, i64 0, i64 %index
%1 = bitcast i8* %0 to <16 x i8>*
%wide.load = load <16 x i8>, <16 x i8>* %1, align 4
%2 = zext <16 x i8> %wide.load to <16 x i32>
%3 = getelementptr inbounds [1024 x i8], [1024 x i8]* @b, i64 0, i64 %index
%4 = bitcast i8* %3 to <16 x i8>*
%wide.load1 = load <16 x i8>, <16 x i8>* %4, align 4
%5 = zext <16 x i8> %wide.load1 to <16 x i32>
%6 = sub nsw <16 x i32> %2, %5
%7 = icmp sgt <16 x i32> %6, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%8 = sub nsw <16 x i32> zeroinitializer, %6
%9 = select <16 x i1> %7, <16 x i32> %6, <16 x i32> %8
%10 = add nsw <16 x i32> %9, %vec.phi
%index.next = add i64 %index, 4
%11 = icmp eq i64 %index.next, 1024
br i1 %11, label %middle.block, label %vector.body
middle.block:
%.lcssa = phi <16 x i32> [ %10, %vector.body ]
%rdx.shuf = shufflevector <16 x i32> %.lcssa, <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx = add <16 x i32> %.lcssa, %rdx.shuf
%rdx.shuf2 = shufflevector <16 x i32> %bin.rdx, <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx2 = add <16 x i32> %bin.rdx, %rdx.shuf2
%rdx.shuf3 = shufflevector <16 x i32> %bin.rdx2, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx3 = add <16 x i32> %bin.rdx2, %rdx.shuf3
%rdx.shuf4 = shufflevector <16 x i32> %bin.rdx3, <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx4 = add <16 x i32> %bin.rdx3, %rdx.shuf4
%12 = extractelement <16 x i32> %bin.rdx4, i32 0
ret i32 %12
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define i32 @sad_16i8_512() "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: sad_16i8_512:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vpxor %xmm0, %xmm0, %xmm0
; CHECK-NEXT: movq $-1024, %rax # imm = 0xFC00
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB11_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vmovdqu a+1024(%rax), %xmm1
; CHECK-NEXT: vpsadbw b+1024(%rax), %xmm1, %xmm1
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
; CHECK-NEXT: addq $4, %rax
; CHECK-NEXT: jne .LBB11_1
; CHECK-NEXT: # %bb.2: # %middle.block
; CHECK-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vextracti128 $1, %ymm0, %xmm1
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
[DAGCombiner] narrow vector binops when extraction is cheap Narrowing vector binops came up in the demanded bits discussion in D52912. I don't think we're going to be able to do this transform in IR as a canonicalization because of the risk of creating unsupported widths for vector ops, but we already have a DAG TLI hook to allow what I was hoping for: isExtractSubvectorCheap(). This is currently enabled for x86, ARM, and AArch64 (although only x86 has existing regression test diffs). This is artificially limited to not look through bitcasts because there are so many test diffs already, but that's marked with a TODO and is a small follow-up. Differential Revision: https://reviews.llvm.org/D53784 llvm-svn: 345602
2018-10-30 22:14:34 +08:00
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vmovd %xmm0, %eax
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
br label %vector.body
vector.body:
%index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
%vec.phi = phi <16 x i32> [ zeroinitializer, %entry ], [ %10, %vector.body ]
%0 = getelementptr inbounds [1024 x i8], [1024 x i8]* @a, i64 0, i64 %index
%1 = bitcast i8* %0 to <16 x i8>*
%wide.load = load <16 x i8>, <16 x i8>* %1, align 4
%2 = zext <16 x i8> %wide.load to <16 x i32>
%3 = getelementptr inbounds [1024 x i8], [1024 x i8]* @b, i64 0, i64 %index
%4 = bitcast i8* %3 to <16 x i8>*
%wide.load1 = load <16 x i8>, <16 x i8>* %4, align 4
%5 = zext <16 x i8> %wide.load1 to <16 x i32>
%6 = sub nsw <16 x i32> %2, %5
%7 = icmp sgt <16 x i32> %6, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%8 = sub nsw <16 x i32> zeroinitializer, %6
%9 = select <16 x i1> %7, <16 x i32> %6, <16 x i32> %8
%10 = add nsw <16 x i32> %9, %vec.phi
%index.next = add i64 %index, 4
%11 = icmp eq i64 %index.next, 1024
br i1 %11, label %middle.block, label %vector.body
middle.block:
%.lcssa = phi <16 x i32> [ %10, %vector.body ]
%rdx.shuf = shufflevector <16 x i32> %.lcssa, <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx = add <16 x i32> %.lcssa, %rdx.shuf
%rdx.shuf2 = shufflevector <16 x i32> %bin.rdx, <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx2 = add <16 x i32> %bin.rdx, %rdx.shuf2
%rdx.shuf3 = shufflevector <16 x i32> %bin.rdx2, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx3 = add <16 x i32> %bin.rdx2, %rdx.shuf3
%rdx.shuf4 = shufflevector <16 x i32> %bin.rdx3, <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx4 = add <16 x i32> %bin.rdx3, %rdx.shuf4
%12 = extractelement <16 x i32> %bin.rdx4, i32 0
ret i32 %12
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @sbto16f32_256(<16 x i16> %a, <16 x float>* %res) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: sbto16f32_256:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
; CHECK-NEXT: kshiftrw $8, %k0, %k1
; CHECK-NEXT: vpmovm2d %k1, %ymm0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vcvtdq2ps %ymm0, %ymm0
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovm2d %k0, %ymm1
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vcvtdq2ps %ymm1, %ymm1
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vmovaps %ymm1, (%rdi)
; CHECK-NEXT: vmovaps %ymm0, 32(%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%1 = sitofp <16 x i1> %mask to <16 x float>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
store <16 x float> %1, <16 x float>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @sbto16f32_512(<16 x i16> %a, <16 x float>* %res) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: sbto16f32_512:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vpmovm2d %k0, %zmm0
; CHECK-NEXT: vcvtdq2ps %zmm0, %zmm0
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vmovaps %zmm0, (%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%1 = sitofp <16 x i1> %mask to <16 x float>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
store <16 x float> %1, <16 x float>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @sbto16f64_256(<16 x i16> %a, <16 x double>* %res) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: sbto16f64_256:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
; CHECK-NEXT: kshiftrw $8, %k0, %k1
; CHECK-NEXT: vpmovm2d %k1, %ymm0
; CHECK-NEXT: vcvtdq2pd %xmm0, %ymm1
; CHECK-NEXT: vextracti128 $1, %ymm0, %xmm0
; CHECK-NEXT: vcvtdq2pd %xmm0, %ymm0
; CHECK-NEXT: vpmovm2d %k0, %ymm2
; CHECK-NEXT: vcvtdq2pd %xmm2, %ymm3
; CHECK-NEXT: vextracti128 $1, %ymm2, %xmm2
; CHECK-NEXT: vcvtdq2pd %xmm2, %ymm2
; CHECK-NEXT: vmovaps %ymm2, 32(%rdi)
; CHECK-NEXT: vmovaps %ymm3, (%rdi)
; CHECK-NEXT: vmovaps %ymm0, 96(%rdi)
; CHECK-NEXT: vmovaps %ymm1, 64(%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
%1 = sitofp <16 x i1> %mask to <16 x double>
store <16 x double> %1, <16 x double>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @sbto16f64_512(<16 x i16> %a, <16 x double>* %res) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: sbto16f64_512:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
; CHECK-NEXT: vpmovm2d %k0, %zmm0
; CHECK-NEXT: vcvtdq2pd %ymm0, %zmm1
; CHECK-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; CHECK-NEXT: vcvtdq2pd %ymm0, %zmm0
; CHECK-NEXT: vmovaps %zmm0, 64(%rdi)
; CHECK-NEXT: vmovaps %zmm1, (%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
%1 = sitofp <16 x i1> %mask to <16 x double>
store <16 x double> %1, <16 x double>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @ubto16f32_256(<16 x i16> %a, <16 x float>* %res) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: ubto16f32_256:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
; CHECK-NEXT: kshiftrw $8, %k0, %k1
; CHECK-NEXT: vpmovm2d %k1, %ymm0
; CHECK-NEXT: vpsrld $31, %ymm0, %ymm0
; CHECK-NEXT: vcvtdq2ps %ymm0, %ymm0
; CHECK-NEXT: vpmovm2d %k0, %ymm1
; CHECK-NEXT: vpsrld $31, %ymm1, %ymm1
; CHECK-NEXT: vcvtdq2ps %ymm1, %ymm1
; CHECK-NEXT: vmovaps %ymm1, (%rdi)
; CHECK-NEXT: vmovaps %ymm0, 32(%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%1 = uitofp <16 x i1> %mask to <16 x float>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
store <16 x float> %1, <16 x float>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @ubto16f32_512(<16 x i16> %a, <16 x float>* %res) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: ubto16f32_512:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vpmovm2d %k0, %zmm0
; CHECK-NEXT: vpsrld $31, %zmm0, %zmm0
; CHECK-NEXT: vcvtdq2ps %zmm0, %zmm0
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vmovaps %zmm0, (%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%1 = uitofp <16 x i1> %mask to <16 x float>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
store <16 x float> %1, <16 x float>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @ubto16f64_256(<16 x i16> %a, <16 x double>* %res) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: ubto16f64_256:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
; CHECK-NEXT: kshiftrw $8, %k0, %k1
; CHECK-NEXT: vpmovm2d %k1, %ymm0
; CHECK-NEXT: vpsrld $31, %ymm0, %ymm0
; CHECK-NEXT: vcvtdq2pd %xmm0, %ymm1
; CHECK-NEXT: vextracti128 $1, %ymm0, %xmm0
; CHECK-NEXT: vcvtdq2pd %xmm0, %ymm0
; CHECK-NEXT: vpmovm2d %k0, %ymm2
; CHECK-NEXT: vpsrld $31, %ymm2, %ymm2
; CHECK-NEXT: vcvtdq2pd %xmm2, %ymm3
; CHECK-NEXT: vextracti128 $1, %ymm2, %xmm2
; CHECK-NEXT: vcvtdq2pd %xmm2, %ymm2
; CHECK-NEXT: vmovaps %ymm2, 32(%rdi)
; CHECK-NEXT: vmovaps %ymm3, (%rdi)
; CHECK-NEXT: vmovaps %ymm0, 96(%rdi)
; CHECK-NEXT: vmovaps %ymm1, 64(%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%1 = uitofp <16 x i1> %mask to <16 x double>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
store <16 x double> %1, <16 x double>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define void @ubto16f64_512(<16 x i16> %a, <16 x double>* %res) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: ubto16f64_512:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpmovw2m %ymm0, %k0
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vpmovm2d %k0, %zmm0
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vpsrld $31, %zmm0, %zmm0
; CHECK-NEXT: vcvtdq2pd %ymm0, %zmm1
; CHECK-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; CHECK-NEXT: vcvtdq2pd %ymm0, %zmm0
; CHECK-NEXT: vmovaps %zmm0, 64(%rdi)
; CHECK-NEXT: vmovaps %zmm1, (%rdi)
; CHECK-NEXT: vzeroupper
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%mask = icmp slt <16 x i16> %a, zeroinitializer
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%1 = uitofp <16 x i1> %mask to <16 x double>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
store <16 x double> %1, <16 x double>* %res
ret void
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define <16 x i16> @test_16f32toub_256(<16 x float>* %ptr, <16 x i16> %passthru) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: test_16f32toub_256:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vcvttps2dq (%rdi), %ymm1
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vpmovdw %ymm1, %xmm1
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vcvttps2dq 32(%rdi), %ymm2
; CHECK-NEXT: vpmovdw %ymm2, %xmm2
; CHECK-NEXT: vinserti128 $1, %xmm2, %ymm1, %ymm1
; CHECK-NEXT: vpsllw $15, %ymm1, %ymm1
; CHECK-NEXT: vpmovw2m %ymm1, %k1
; CHECK-NEXT: vmovdqu16 %ymm0, %ymm0 {%k1} {z}
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%a = load <16 x float>, <16 x float>* %ptr
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%mask = fptoui <16 x float> %a to <16 x i1>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%select = select <16 x i1> %mask, <16 x i16> %passthru, <16 x i16> zeroinitializer
ret <16 x i16> %select
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define <16 x i16> @test_16f32toub_512(<16 x float>* %ptr, <16 x i16> %passthru) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: test_16f32toub_512:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vcvttps2dq (%rdi), %zmm1
; CHECK-NEXT: vpslld $31, %zmm1, %zmm1
[X86] Use vpmovq2m/vpmovd2m for truncate to vXi1 when possible. Previously we used vptestmd, but the scheduling data for SKX says vpmovq2m/vpmovd2m is lower latency. We already used vpmovb2m/vpmovw2m for byte/word truncates. So this is more consistent anyway. llvm-svn: 325534
2018-02-20 06:07:31 +08:00
; CHECK-NEXT: vpmovd2m %zmm1, %k1
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vmovdqu16 %ymm0, %ymm0 {%k1} {z}
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%a = load <16 x float>, <16 x float>* %ptr
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%mask = fptoui <16 x float> %a to <16 x i1>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%select = select <16 x i1> %mask, <16 x i16> %passthru, <16 x i16> zeroinitializer
ret <16 x i16> %select
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define <16 x i16> @test_16f32tosb_256(<16 x float>* %ptr, <16 x i16> %passthru) "min-legal-vector-width"="256" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: test_16f32tosb_256:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vcvttps2dq (%rdi), %ymm1
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: vpmovdw %ymm1, %xmm1
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vcvttps2dq 32(%rdi), %ymm2
; CHECK-NEXT: vpmovdw %ymm2, %xmm2
; CHECK-NEXT: vinserti128 $1, %xmm2, %ymm1, %ymm1
; CHECK-NEXT: vpsllw $15, %ymm1, %ymm1
; CHECK-NEXT: vpmovw2m %ymm1, %k1
; CHECK-NEXT: vmovdqu16 %ymm0, %ymm0 {%k1} {z}
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%a = load <16 x float>, <16 x float>* %ptr
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%mask = fptosi <16 x float> %a to <16 x i1>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%select = select <16 x i1> %mask, <16 x i16> %passthru, <16 x i16> zeroinitializer
ret <16 x i16> %select
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}
[X86] Change X86 backend to look for 'min-legal-vector-width' attribute instead of 'required-vector-width' when determining whether 512-bit vectors should be legal. The required-vector-width attribute was only used for backend testing and has never been generated by clang. I believe clang is now generating min-legal-vector-width for vector uses in user code. With this I believe passing -mprefer-vector-width=256 to clang should prevent use of zmm registers in the generated assembly unless the user used a 512-bit intrinsic in their source code. llvm-svn: 345317
2018-10-26 05:16:06 +08:00
define <16 x i16> @test_16f32tosb_512(<16 x float>* %ptr, <16 x i16> %passthru) "min-legal-vector-width"="512" {
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-LABEL: test_16f32tosb_512:
; CHECK: # %bb.0:
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vcvttps2dq (%rdi), %zmm1
[X86] Use vpmovq2m/vpmovd2m for truncate to vXi1 when possible. Previously we used vptestmd, but the scheduling data for SKX says vpmovq2m/vpmovd2m is lower latency. We already used vpmovb2m/vpmovw2m for byte/word truncates. So this is more consistent anyway. llvm-svn: 325534
2018-02-20 06:07:31 +08:00
; CHECK-NEXT: vpmovd2m %zmm1, %k1
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
; CHECK-NEXT: vmovdqu16 %ymm0, %ymm0 {%k1} {z}
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
; CHECK-NEXT: retq
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%a = load <16 x float>, <16 x float>* %ptr
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
%mask = fptosi <16 x float> %a to <16 x i1>
[X86] Update some required-vector-width.ll test cases to not pass 512-bit vectors in arguments or return. ABI for these would require 512 bits support so we don't want to test that. llvm-svn: 324845
2018-02-12 02:52:16 +08:00
%select = select <16 x i1> %mask, <16 x i16> %passthru, <16 x i16> zeroinitializer
ret <16 x i16> %select
[X86] Don't make 512-bit vectors legal when preferred vector width is 256 bits and 512 bits aren't required This patch adds a new function attribute "required-vector-width" that can be set by the frontend to indicate the maximum vector width present in the original source code. The idea is that this would be set based on ABI requirements, intrinsics or explicit vector types being used, maybe simd pragmas, etc. The backend will then use this information to determine if its save to make 512-bit vectors illegal when the preference is for 256-bit vectors. For code that has no vectors in it originally and only get vectors through the loop and slp vectorizers this allows us to generate code largely similar to our AVX2 only output while still enabling AVX512 features like mask registers and gather/scatter. The loop vectorizer doesn't always obey TTI and will create oversized vectors with the expectation the backend will legalize it. In order to avoid changing the vectorizer and potentially harm our AVX2 codegen this patch tries to make the legalizer behavior similar. This is restricted to CPUs that support AVX512F and AVX512VL so that we have good fallback options to use 128 and 256-bit vectors and still get masking. I've qualified every place I could find in X86ISelLowering.cpp and added tests cases for many of them with 2 different values for the attribute to see the codegen differences. We still need to do frontend work for the attribute and teach the inliner how to merge it, etc. But this gets the codegen layer ready for it. Differential Revision: https://reviews.llvm.org/D42724 llvm-svn: 324834
2018-02-11 16:06:27 +08:00
}