https://github.com/mikolaj-pirog updated https://github.com/llvm/llvm-project/pull/168061
From 928c4e4d65722ee9abd7142b520cbe6a21348e78 Mon Sep 17 00:00:00 2001 From: "Pirog, Mikolaj Maciej" <[email protected]> Date: Fri, 14 Nov 2025 14:51:10 +0100 Subject: [PATCH 1/6] Enable APX and AVX10.2 on NVL --- llvm/lib/Target/X86/X86.td | 12 +++++++++++- llvm/lib/TargetParser/X86TargetParser.cpp | 4 +++- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/llvm/lib/Target/X86/X86.td b/llvm/lib/Target/X86/X86.td index 9e291a6ae431f..27ec052cfda40 100644 --- a/llvm/lib/Target/X86/X86.td +++ b/llvm/lib/Target/X86/X86.td @@ -1334,8 +1334,18 @@ def ProcessorFeatures { !listremove(ARLSFeatures, [FeatureWIDEKL]); // Novalake + list<SubtargetFeature> NVLAdditionalFeatures = [FeatureAVX10_2, + FeatureMOVRS, + FeatureEGPR, + FeaturePush2Pop2, + FeaturePPX, + FeatureNF, + FeatureNDD, + FeatureZU, + FeatureCCMP, + FeaturePREFETCHI]; list<SubtargetFeature> NVLFeatures = - !listconcat(PTLFeatures, [FeaturePREFETCHI]); + !listconcat(PTLFeatures, NVLAdditionalFeatures); // Clearwaterforest list<SubtargetFeature> CWFAdditionalFeatures = [FeaturePREFETCHI, diff --git a/llvm/lib/TargetParser/X86TargetParser.cpp b/llvm/lib/TargetParser/X86TargetParser.cpp index 37e8ad986aa55..ad0d7b38ae1b3 100644 --- a/llvm/lib/TargetParser/X86TargetParser.cpp +++ b/llvm/lib/TargetParser/X86TargetParser.cpp @@ -176,7 +176,9 @@ constexpr FeatureBitset FeaturesArrowlakeS = constexpr FeatureBitset FeaturesPantherlake = (FeaturesArrowlakeS ^ FeatureWIDEKL); constexpr FeatureBitset FeaturesNovalake = - FeaturesPantherlake | FeaturePREFETCHI; + FeaturesPantherlake | FeaturePREFETCHI | FeatureAVX10_2 | FeatureMOVRS | + FeatureEGPR | FeatureZU | FeatureCCMP | FeaturePush2Pop2 | FeaturePPX | + FeatureNDD | FeatureNF; constexpr FeatureBitset FeaturesClearwaterforest = (FeaturesSierraforest ^ FeatureWIDEKL) | FeatureAVXVNNIINT16 | FeatureSHA512 | FeatureSM3 | FeatureSM4 | FeaturePREFETCHI | FeatureUSERMSR; From 26e473ae42e6e6b20ac2022e5c752b17b990e45c Mon Sep 17 00:00:00 2001 From: "Pirog, Mikolaj Maciej" <[email protected]> Date: Fri, 14 Nov 2025 16:26:53 +0100 Subject: [PATCH 2/6] Fix test --- .../Preprocessor/predefined-arch-macros.c | 72 +++++++++++++++---- 1 file changed, 60 insertions(+), 12 deletions(-) diff --git a/clang/test/Preprocessor/predefined-arch-macros.c b/clang/test/Preprocessor/predefined-arch-macros.c index cf2cd4a10b056..a70174d41e1b9 100644 --- a/clang/test/Preprocessor/predefined-arch-macros.c +++ b/clang/test/Preprocessor/predefined-arch-macros.c @@ -2525,16 +2525,33 @@ // RUN: %clang -march=wildcatlake -m32 -E -dM %s -o - 2>&1 \ // RUN: -target i386-unknown-linux \ // RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M32,CHECK_ARLS_M32,CHECK_NKL_M32 -// RUN: %clang -march=novalake -m32 -E -dM %s -o - 2>&1 \ -// RUN: -target i386-unknown-linux \ -// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M32,CHECK_ARLS_M32,CHECK_NVL_M32,CHECK_NKL_M32 // RUN: %clang -march=clearwaterforest -m32 -E -dM %s -o - 2>&1 \ // RUN: -target i386-unknown-linux \ -// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_SRF_M32,CHECK_ARLS_M32,CHECK_NVL_M32,CHECK_UMSR_M32,CHECK_NKL_M32 +// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_SRF_M32,CHECK_ARLS_M32,CHECK_UMSR_M32,CHECK_CWF_M32,CHECK_NKL_M32 +// RUN: %clang -march=novalake -m32 -E -dM %s -o - 2>&1 \ +// RUN: -target i386-unknown-linux \ +// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M32,CHECK_ARLS_M32,CHECK_CWF_M32,CHECK_NVL_M32,CHECK_NKL_M32 // CHECK_ARL_M32: #define __ADX__ 1 // CHECK_ARL_M32: #define __AES__ 1 -// CHECK_ARL_M32: #define __AVX2__ 1 // CHECK_ARL_M32-NOT: AVX512 +// CHECK_NVL_M32: #define __AVX10_1_512__ 1 +// CHECK_NVL_M32: #define __AVX10_1__ 1 +// CHECK_NVL_M32: #define __AVX10_2_512__ 1 +// CHECK_NVL_M32: #define __AVX10_2__ 1 +// CHECK_ARL_M32: #define __AVX2__ 1 +// CHECK_NVL_M32: #define __AVX512BF16__ 1 +// CHECK_NVL_M32: #define __AVX512BITALG__ 1 +// CHECK_NVL_M32: #define __AVX512BW__ 1 +// CHECK_NVL_M32: #define __AVX512CD__ 1 +// CHECK_NVL_M32: #define __AVX512DQ__ 1 +// CHECK_NVL_M32: #define __AVX512FP16__ 1 +// CHECK_NVL_M32: #define __AVX512F__ 1 +// CHECK_NVL_M32: #define __AVX512IFMA__ 1 +// CHECK_NVL_M32: #define __AVX512VBMI2__ 1 +// CHECK_NVL_M32: #define __AVX512VBMI__ 1 +// CHECK_NVL_M32: #define __AVX512VL__ 1 +// CHECK_NVL_M32: #define __AVX512VNNI__ 1 +// CHECK_NVL_M32: #define __AVX512VPOPCNTDQ__ 1 // CHECK_ARL_M32: #define __AVXIFMA__ 1 // CHECK_ARL_M32: #define __AVXNECONVERT__ 1 // CHECK_ARL_M32-NOT: #define __AVXVNNIINT16__ 1 @@ -2549,6 +2566,7 @@ // CHECK_ARL_M32: #define __CLFLUSHOPT__ 1 // CHECK_ARL_M32: #define __CLWB__ 1 // CHECK_ARL_M32: #define __CMPCCXADD__ 1 +// CHECK_NVL_M32: #define __EGPR__ 1 // CHECK_ARL_M32: #define __ENQCMD__ 1 // CHECK_ARL_M32: #define __F16C__ 1 // CHECK_ARL_M32: #define __FMA__ 1 @@ -2564,15 +2582,20 @@ // CHECK_ARL_M32: #define __MOVBE__ 1 // CHECK_ARL_M32: #define __MOVDIR64B__ 1 // CHECK_ARL_M32: #define __MOVDIRI__ 1 +// CHECK_NVL_M32: #define __MOVRS__ 1 +// CHECK_NVL_M32: #define __NDD__ 1 +// CHECK_NVL_M32: #define __NF__ 1 // CHECK_ARL_M32: #define __PCLMUL__ 1 // CHECK_ARL_M32: #define __PCONFIG__ 1 // CHECK_ARL_M32: #define __PKU__ 1 // CHECK_ARL_M32: #define __POPCNT__ 1 +// CHECK_NVL_M32: #define __PPX__ 1 // CHECK_ARL_M32-NOT: #define __PREFETCHI__ 1 // CHECK_ARLS_M32-NOT: #define __PREFETCHI__ 1 -// CHECK_NVL_M32: #define __PREFETCHI__ 1 +// CHECK_CWF_M32: #define __PREFETCHI__ 1 // CHECK_ARL_M32: #define __PRFCHW__ 1 // CHECK_ARL_M32: #define __PTWRITE__ 1 +// CHECK_NVL_M32: #define __PUSH2POP2__ 1 // CHECK_ARL_M32-NOT: #define __RAOINT__ 1 // CHECK_ARL_M32: #define __RDPID__ 1 // CHECK_ARL_M32: #define __RDRND__ 1 @@ -2607,6 +2630,7 @@ // CHECK_ARL_M32: #define __XSAVEOPT__ 1 // CHECK_ARL_M32: #define __XSAVES__ 1 // CHECK_ARL_M32: #define __XSAVE__ 1 +// CHECK_NVL_M32: #define __ZU__ 1 // CHECK_ARL_M32: #define __corei7 1 // CHECK_ARL_M32: #define __corei7__ 1 // CHECK_ARL_M32: #define __i386 1 @@ -2635,16 +2659,33 @@ // RUN: %clang -march=wildcatlake -m64 -E -dM %s -o - 2>&1 \ // RUN: -target i386-unknown-linux \ // RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M64,CHECK_ARLS_M64,CHECK_NKL_M64 -// RUN: %clang -march=novalake -m64 -E -dM %s -o - 2>&1 \ -// RUN: -target i386-unknown-linux \ -// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M64,CHECK_ARLS_M64,CHECK_NVL_M64,CHECK_NKL_M64 // RUN: %clang -march=clearwaterforest -m64 -E -dM %s -o - 2>&1 \ // RUN: -target i386-unknown-linux \ -// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M64,CHECK_SRF_M64,CHECK_ARLS_M64,CHECK_NVL_M64,CHECK_UMSR_M64,CHECK_NKL_M64 +// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_SRF_M64,CHECK_ARLS_M64,CHECK_UMSR_M64,CHECK_CWF_M64,CHECK_NKL_M64 +// RUN: %clang -march=novalake -m64 -E -dM %s -o - 2>&1 \ +// RUN: -target i386-unknown-linux \ +// RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M64,CHECK_ARLS_M64,CHECK_CWF_M64,CHECK_NVL_M64,CHECK_NKL_M64 // CHECK_ARL_M64: #define __ADX__ 1 // CHECK_ARL_M64: #define __AES__ 1 -// CHECK_ARL_M64: #define __AVX2__ 1 // CHECK_ARL_M64-NOT: AVX512 +// CHECK_NVL_M64: #define __AVX10_1_512__ 1 +// CHECK_NVL_M64: #define __AVX10_1__ 1 +// CHECK_NVL_M64: #define __AVX10_2_512__ 1 +// CHECK_NVL_M64: #define __AVX10_2__ 1 +// CHECK_ARL_M64: #define __AVX2__ 1 +// CHECK_NVL_M64: #define __AVX512BF16__ 1 +// CHECK_NVL_M64: #define __AVX512BITALG__ 1 +// CHECK_NVL_M64: #define __AVX512BW__ 1 +// CHECK_NVL_M64: #define __AVX512CD__ 1 +// CHECK_NVL_M64: #define __AVX512DQ__ 1 +// CHECK_NVL_M64: #define __AVX512FP16__ 1 +// CHECK_NVL_M64: #define __AVX512F__ 1 +// CHECK_NVL_M64: #define __AVX512IFMA__ 1 +// CHECK_NVL_M64: #define __AVX512VBMI2__ 1 +// CHECK_NVL_M64: #define __AVX512VBMI__ 1 +// CHECK_NVL_M64: #define __AVX512VL__ 1 +// CHECK_NVL_M64: #define __AVX512VNNI__ 1 +// CHECK_NVL_M64: #define __AVX512VPOPCNTDQ__ 1 // CHECK_ARL_M64: #define __AVXIFMA__ 1 // CHECK_ARL_M64: #define __AVXNECONVERT__ 1 // CHECK_ARL_M64-NOT: #define __AVXVNNIINT16__ 1 @@ -2654,11 +2695,13 @@ // CHECK_ARL_M64: #define __AVX__ 1 // CHECK_ARL_M64: #define __BMI2__ 1 // CHECK_ARL_M64: #define __BMI__ 1 +// CHECK_NVL_M64: #define __CCMP__ 1 // CHECK_ARLS_M64-NOT: __CLDEMOTE__ // CHECK_SRF_M64: #define __CLDEMOTE__ 1 // CHECK_ARL_M64: #define __CLFLUSHOPT__ 1 // CHECK_ARL_M64: #define __CLWB__ 1 // CHECK_ARL_M64: #define __CMPCCXADD__ 1 +// CHECK_NVL_M64: #define __EGPR__ 1 // CHECK_ARL_M64: #define __ENQCMD__ 1 // CHECK_ARL_M64: #define __F16C__ 1 // CHECK_ARL_M64: #define __FMA__ 1 @@ -2674,13 +2717,17 @@ // CHECK_ARL_M64: #define __MOVBE__ 1 // CHECK_ARL_M64: #define __MOVDIR64B__ 1 // CHECK_ARL_M64: #define __MOVDIRI__ 1 +// CHECK_NVL_M64: #define __MOVRS__ 1 +// CHECK_NVL_M64: #define __NDD__ 1 +// CHECK_NVL_M64: #define __NF__ 1 // CHECK_ARL_M64: #define __PCLMUL__ 1 // CHECK_ARL_M64: #define __PCONFIG__ 1 // CHECK_ARL_M64: #define __PKU__ 1 // CHECK_ARL_M64: #define __POPCNT__ 1 +// CHECK_NVL_M64: #define __PPX__ 1 // CHECK_ARL_M64-NOT: #define __PREFETCHI__ 1 // CHECK_ARLS_M64-NOT: #define __PREFETCHI__ 1 -// CHECK_NVL_M64: #define __PREFETCHI__ 1 +// CHECK_CWF_M64: #define __PREFETCHI__ 1 // CHECK_ARL_M64: #define __PRFCHW__ 1 // CHECK_ARL_M64: #define __PTWRITE__ 1 // CHECK_ARL_M64-NOT: #define __RAOINT__ 1 @@ -2718,6 +2765,7 @@ // CHECK_ARL_M64: #define __XSAVEOPT__ 1 // CHECK_ARL_M64: #define __XSAVES__ 1 // CHECK_ARL_M64: #define __XSAVE__ 1 +// CHECK_NVL_M64: #define __ZU__ 1 // CHECK_ARL_M64: #define __amd64 1 // CHECK_ARL_M64: #define __amd64__ 1 // CHECK_ARL_M64: #define __corei7 1 From 6d35b7d32435f370cefd057c3610569411f58456 Mon Sep 17 00:00:00 2001 From: "Pirog, Mikolaj Maciej" <[email protected]> Date: Fri, 14 Nov 2025 16:36:27 +0100 Subject: [PATCH 3/6] Fix test --- clang/test/Preprocessor/predefined-arch-macros.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/clang/test/Preprocessor/predefined-arch-macros.c b/clang/test/Preprocessor/predefined-arch-macros.c index a70174d41e1b9..094289b0bde59 100644 --- a/clang/test/Preprocessor/predefined-arch-macros.c +++ b/clang/test/Preprocessor/predefined-arch-macros.c @@ -2561,6 +2561,7 @@ // CHECK_ARL_M32: #define __AVX__ 1 // CHECK_ARL_M32: #define __BMI2__ 1 // CHECK_ARL_M32: #define __BMI__ 1 +// CHECK_NVL_M32: #define __CCMP__ 1 // CHECK_ARLS_M32-NOT: __CLDEMOTE__ // CHECK_SRF_M32: #define __CLDEMOTE__ 1 // CHECK_ARL_M32: #define __CLFLUSHOPT__ 1 @@ -2730,6 +2731,7 @@ // CHECK_CWF_M64: #define __PREFETCHI__ 1 // CHECK_ARL_M64: #define __PRFCHW__ 1 // CHECK_ARL_M64: #define __PTWRITE__ 1 +// CHECK_NVL_M64: #define __PUSH2POP2__ 1 // CHECK_ARL_M64-NOT: #define __RAOINT__ 1 // CHECK_ARL_M64: #define __RDPID__ 1 // CHECK_ARL_M64: #define __RDRND__ 1 From 8904d11d4910e2d8d1886ea80895f84cce8d4d4c Mon Sep 17 00:00:00 2001 From: "Pirog, Mikolaj Maciej" <[email protected]> Date: Mon, 17 Nov 2025 11:44:00 +0100 Subject: [PATCH 4/6] Reviewer suggestions --- clang/test/Preprocessor/predefined-arch-macros.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/clang/test/Preprocessor/predefined-arch-macros.c b/clang/test/Preprocessor/predefined-arch-macros.c index 094289b0bde59..d11d2a25b4672 100644 --- a/clang/test/Preprocessor/predefined-arch-macros.c +++ b/clang/test/Preprocessor/predefined-arch-macros.c @@ -2534,10 +2534,9 @@ // CHECK_ARL_M32: #define __ADX__ 1 // CHECK_ARL_M32: #define __AES__ 1 // CHECK_ARL_M32-NOT: AVX512 -// CHECK_NVL_M32: #define __AVX10_1_512__ 1 // CHECK_NVL_M32: #define __AVX10_1__ 1 -// CHECK_NVL_M32: #define __AVX10_2_512__ 1 // CHECK_NVL_M32: #define __AVX10_2__ 1 +// AVX2 needs to be here, not after AES because otherwise NVL fails // CHECK_ARL_M32: #define __AVX2__ 1 // CHECK_NVL_M32: #define __AVX512BF16__ 1 // CHECK_NVL_M32: #define __AVX512BITALG__ 1 @@ -2669,9 +2668,7 @@ // CHECK_ARL_M64: #define __ADX__ 1 // CHECK_ARL_M64: #define __AES__ 1 // CHECK_ARL_M64-NOT: AVX512 -// CHECK_NVL_M64: #define __AVX10_1_512__ 1 // CHECK_NVL_M64: #define __AVX10_1__ 1 -// CHECK_NVL_M64: #define __AVX10_2_512__ 1 // CHECK_NVL_M64: #define __AVX10_2__ 1 // CHECK_ARL_M64: #define __AVX2__ 1 // CHECK_NVL_M64: #define __AVX512BF16__ 1 From a997903ac6a5b5698bc202ebef831b344c1ccde7 Mon Sep 17 00:00:00 2001 From: "Pirog, Mikolaj Maciej" <[email protected]> Date: Mon, 17 Nov 2025 14:48:21 +0100 Subject: [PATCH 5/6] Shuffle check around --- clang/test/Preprocessor/predefined-arch-macros.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/clang/test/Preprocessor/predefined-arch-macros.c b/clang/test/Preprocessor/predefined-arch-macros.c index d11d2a25b4672..74df6348bf4e8 100644 --- a/clang/test/Preprocessor/predefined-arch-macros.c +++ b/clang/test/Preprocessor/predefined-arch-macros.c @@ -2533,7 +2533,6 @@ // RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M32,CHECK_ARLS_M32,CHECK_CWF_M32,CHECK_NVL_M32,CHECK_NKL_M32 // CHECK_ARL_M32: #define __ADX__ 1 // CHECK_ARL_M32: #define __AES__ 1 -// CHECK_ARL_M32-NOT: AVX512 // CHECK_NVL_M32: #define __AVX10_1__ 1 // CHECK_NVL_M32: #define __AVX10_2__ 1 // AVX2 needs to be here, not after AES because otherwise NVL fails @@ -2551,6 +2550,7 @@ // CHECK_NVL_M32: #define __AVX512VL__ 1 // CHECK_NVL_M32: #define __AVX512VNNI__ 1 // CHECK_NVL_M32: #define __AVX512VPOPCNTDQ__ 1 +// CHECK_ARL_M32-NOT: AVX512 // CHECK_ARL_M32: #define __AVXIFMA__ 1 // CHECK_ARL_M32: #define __AVXNECONVERT__ 1 // CHECK_ARL_M32-NOT: #define __AVXVNNIINT16__ 1 @@ -2667,7 +2667,6 @@ // RUN: | FileCheck -match-full-lines %s -check-prefixes=CHECK_ARL_M64,CHECK_ARLS_M64,CHECK_CWF_M64,CHECK_NVL_M64,CHECK_NKL_M64 // CHECK_ARL_M64: #define __ADX__ 1 // CHECK_ARL_M64: #define __AES__ 1 -// CHECK_ARL_M64-NOT: AVX512 // CHECK_NVL_M64: #define __AVX10_1__ 1 // CHECK_NVL_M64: #define __AVX10_2__ 1 // CHECK_ARL_M64: #define __AVX2__ 1 @@ -2684,6 +2683,7 @@ // CHECK_NVL_M64: #define __AVX512VL__ 1 // CHECK_NVL_M64: #define __AVX512VNNI__ 1 // CHECK_NVL_M64: #define __AVX512VPOPCNTDQ__ 1 +// CHECK_ARL_M64-NOT: AVX512 // CHECK_ARL_M64: #define __AVXIFMA__ 1 // CHECK_ARL_M64: #define __AVXNECONVERT__ 1 // CHECK_ARL_M64-NOT: #define __AVXVNNIINT16__ 1 From fba4231689853b5b1b40553813e5c03d5ab6e732 Mon Sep 17 00:00:00 2001 From: "Pirog, Mikolaj Maciej" <[email protected]> Date: Mon, 17 Nov 2025 14:49:04 +0100 Subject: [PATCH 6/6] Change comment --- clang/test/Preprocessor/predefined-arch-macros.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/clang/test/Preprocessor/predefined-arch-macros.c b/clang/test/Preprocessor/predefined-arch-macros.c index 74df6348bf4e8..27feeb57b5de2 100644 --- a/clang/test/Preprocessor/predefined-arch-macros.c +++ b/clang/test/Preprocessor/predefined-arch-macros.c @@ -2535,7 +2535,6 @@ // CHECK_ARL_M32: #define __AES__ 1 // CHECK_NVL_M32: #define __AVX10_1__ 1 // CHECK_NVL_M32: #define __AVX10_2__ 1 -// AVX2 needs to be here, not after AES because otherwise NVL fails // CHECK_ARL_M32: #define __AVX2__ 1 // CHECK_NVL_M32: #define __AVX512BF16__ 1 // CHECK_NVL_M32: #define __AVX512BITALG__ 1 @@ -2550,6 +2549,8 @@ // CHECK_NVL_M32: #define __AVX512VL__ 1 // CHECK_NVL_M32: #define __AVX512VNNI__ 1 // CHECK_NVL_M32: #define __AVX512VPOPCNTDQ__ 1 +// We check for NOT AVX512 after all checks for AVX512, so +// if we missed some check on NVL, the test will fail. // CHECK_ARL_M32-NOT: AVX512 // CHECK_ARL_M32: #define __AVXIFMA__ 1 // CHECK_ARL_M32: #define __AVXNECONVERT__ 1 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
