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/PowerPC/fp-strict-f128.ll

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

272 lines
8.9 KiB
LLVM
Raw Normal View History

[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[PowerPC] Enable default support of quad precision operations Summary: Remove option guarding support of quad precision operations. Reviewers: nemanjai, #powerpc, steven.zhang Reviewed By: nemanjai, #powerpc, steven.zhang Subscribers: qiucf, wuzish, nemanjai, hiraditya, kbarton, shchenz, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D83437
2020-07-09 06:07:34 +08:00
; RUN: llc -verify-machineinstrs -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
; RUN: < %s -mtriple=powerpc64le-unknown-linux -mcpu=pwr9 | FileCheck %s
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; RUN: llc -verify-machineinstrs -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
; RUN: < %s -mtriple=powerpc64le-unknown-linux -mcpu=pwr8 | FileCheck %s --check-prefix=CHECK-P8
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
declare fp128 @llvm.experimental.constrained.fadd.f128(fp128, fp128, metadata, metadata)
declare fp128 @llvm.experimental.constrained.fsub.f128(fp128, fp128, metadata, metadata)
declare fp128 @llvm.experimental.constrained.fmul.f128(fp128, fp128, metadata, metadata)
declare fp128 @llvm.experimental.constrained.fdiv.f128(fp128, fp128, metadata, metadata)
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
declare fp128 @llvm.experimental.constrained.fma.f128(fp128, fp128, fp128, metadata, metadata)
declare fp128 @llvm.experimental.constrained.sqrt.f128(fp128, metadata, metadata)
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fadd_f128(fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
; CHECK-LABEL: fadd_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fadd_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
%res = call fp128 @llvm.experimental.constrained.fadd.f128(
fp128 %f1, fp128 %f2,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fsub_f128(fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
; CHECK-LABEL: fsub_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xssubqp v2, v2, v3
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fsub_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: bl __subkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
%res = call fp128 @llvm.experimental.constrained.fsub.f128(
fp128 %f1, fp128 %f2,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fmul_f128(fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
; CHECK-LABEL: fmul_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xsmulqp v2, v2, v3
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fmul_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: bl __mulkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
%res = call fp128 @llvm.experimental.constrained.fmul.f128(
fp128 %f1, fp128 %f2,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fdiv_f128(fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
; CHECK-LABEL: fdiv_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xsdivqp v2, v2, v3
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fdiv_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: bl __divkf3
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
%res = call fp128 @llvm.experimental.constrained.fdiv.f128(
fp128 %f1, fp128 %f2,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add strict-fp intrinsic to FP arithmetic This patch adds basic strict-fp intrinsics support to PowerPC backend, including basic arithmetic operations (add/sub/mul/div). Reviewed By: steven.zhang, andrew.w.kaylor Differential Revision: https://reviews.llvm.org/D63916
2020-03-12 17:02:54 +08:00
ret fp128 %res
}
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fmadd_f128(fp128 %f0, fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
; CHECK-LABEL: fmadd_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xsmaddqp v4, v2, v3
; CHECK-NEXT: vmr v2, v4
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fmadd_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
[PowerPC][FP128] Fix the incorrect signature for math library call The runtime library has two family library implementation for ppc_fp128 and fp128. For IBM Long double(ppc_fp128), it is suffixed with 'l', i.e(sqrtl). For IEEE Long double(fp128), it is suffixed with "ieee128" or "f128". We miss to map several libcall for IEEE Long double. Reviewed By: qiucf Differential Revision: https://reviews.llvm.org/D91675
2020-12-14 15:39:06 +08:00
; CHECK-P8-NEXT: bl fmaf128
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
%res = call fp128 @llvm.experimental.constrained.fma.f128(
fp128 %f0, fp128 %f1, fp128 %f2,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fmsub_f128(fp128 %f0, fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
; CHECK-LABEL: fmsub_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xsmsubqp v4, v2, v3
; CHECK-NEXT: vmr v2, v4
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fmsub_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: li r9, 1
[PowerPC] Materialize i64 constants by enumerated patterns. Summary: Some constants can be handled with less instructions than our current results. And it seems our original approach is not very easy to extend. Therefore this patch proposes to materialize all 64-bit constants by enumerated patterns. I traversed almost all constants to verified the functionality of these pattens. A traversed comparison of the number of instructions used by the original method and the new method has also been completed, where no degradation was caused by this patch. This patch also passed Bootstrap test and SPEC test. Improvements of this patch are shown in llvm/test/CodeGen/PowerPC/constants-i64.ll Reviewed By: steven.zhang, stefanp Differential Revision: https://reviews.llvm.org/D92089
2020-12-21 13:21:07 +08:00
; CHECK-P8-NEXT: rldic r9, r9, 63, 0
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: xor r8, r8, r9
[PowerPC][FP128] Fix the incorrect signature for math library call The runtime library has two family library implementation for ppc_fp128 and fp128. For IBM Long double(ppc_fp128), it is suffixed with 'l', i.e(sqrtl). For IEEE Long double(fp128), it is suffixed with "ieee128" or "f128". We miss to map several libcall for IEEE Long double. Reviewed By: qiucf Differential Revision: https://reviews.llvm.org/D91675
2020-12-14 15:39:06 +08:00
; CHECK-P8-NEXT: bl fmaf128
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
%neg = fneg fp128 %f2
%res = call fp128 @llvm.experimental.constrained.fma.f128(
fp128 %f0, fp128 %f1, fp128 %neg,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fnmadd_f128(fp128 %f0, fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
; CHECK-LABEL: fnmadd_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xsnmaddqp v4, v2, v3
; CHECK-NEXT: vmr v2, v4
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fnmadd_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
[PowerPC][FP128] Fix the incorrect signature for math library call The runtime library has two family library implementation for ppc_fp128 and fp128. For IBM Long double(ppc_fp128), it is suffixed with 'l', i.e(sqrtl). For IEEE Long double(fp128), it is suffixed with "ieee128" or "f128". We miss to map several libcall for IEEE Long double. Reviewed By: qiucf Differential Revision: https://reviews.llvm.org/D91675
2020-12-14 15:39:06 +08:00
; CHECK-P8-NEXT: bl fmaf128
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r5, 1
[PowerPC] Materialize i64 constants by enumerated patterns. Summary: Some constants can be handled with less instructions than our current results. And it seems our original approach is not very easy to extend. Therefore this patch proposes to materialize all 64-bit constants by enumerated patterns. I traversed almost all constants to verified the functionality of these pattens. A traversed comparison of the number of instructions used by the original method and the new method has also been completed, where no degradation was caused by this patch. This patch also passed Bootstrap test and SPEC test. Improvements of this patch are shown in llvm/test/CodeGen/PowerPC/constants-i64.ll Reviewed By: steven.zhang, stefanp Differential Revision: https://reviews.llvm.org/D92089
2020-12-21 13:21:07 +08:00
; CHECK-P8-NEXT: rldic r5, r5, 63, 0
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: xor r4, r4, r5
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
%fma = call fp128 @llvm.experimental.constrained.fma.f128(
fp128 %f0, fp128 %f1, fp128 %f2,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
%res = fneg fp128 %fma
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fnmsub_f128(fp128 %f0, fp128 %f1, fp128 %f2) #0 {
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
; CHECK-LABEL: fnmsub_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xsnmsubqp v4, v2, v3
; CHECK-NEXT: vmr v2, v4
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fnmsub_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: .cfi_def_cfa_offset 48
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: .cfi_offset r30, -16
; CHECK-P8-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: li r9, 1
[PowerPC] Materialize i64 constants by enumerated patterns. Summary: Some constants can be handled with less instructions than our current results. And it seems our original approach is not very easy to extend. Therefore this patch proposes to materialize all 64-bit constants by enumerated patterns. I traversed almost all constants to verified the functionality of these pattens. A traversed comparison of the number of instructions used by the original method and the new method has also been completed, where no degradation was caused by this patch. This patch also passed Bootstrap test and SPEC test. Improvements of this patch are shown in llvm/test/CodeGen/PowerPC/constants-i64.ll Reviewed By: steven.zhang, stefanp Differential Revision: https://reviews.llvm.org/D92089
2020-12-21 13:21:07 +08:00
; CHECK-P8-NEXT: rldic r30, r9, 63, 0
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: xor r8, r8, r30
[PowerPC][FP128] Fix the incorrect signature for math library call The runtime library has two family library implementation for ppc_fp128 and fp128. For IBM Long double(ppc_fp128), it is suffixed with 'l', i.e(sqrtl). For IEEE Long double(fp128), it is suffixed with "ieee128" or "f128". We miss to map several libcall for IEEE Long double. Reviewed By: qiucf Differential Revision: https://reviews.llvm.org/D91675
2020-12-14 15:39:06 +08:00
; CHECK-P8-NEXT: bl fmaf128
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: xor r4, r4, r30
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
%neg = fneg fp128 %f2
%fma = call fp128 @llvm.experimental.constrained.fma.f128(
fp128 %f0, fp128 %f1, fp128 %neg,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
%res = fneg fp128 %fma
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
define fp128 @fsqrt_f128(fp128 %f1) #0 {
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
; CHECK-LABEL: fsqrt_f128:
; CHECK: # %bb.0:
; CHECK-NEXT: xssqrtqp v2, v2
; CHECK-NEXT: blr
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
;
; CHECK-P8-LABEL: fsqrt_f128:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: mflr r0
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
[PowerPC][FP128] Fix the incorrect signature for math library call The runtime library has two family library implementation for ppc_fp128 and fp128. For IBM Long double(ppc_fp128), it is suffixed with 'l', i.e(sqrtl). For IEEE Long double(fp128), it is suffixed with "ieee128" or "f128". We miss to map several libcall for IEEE Long double. Reviewed By: qiucf Differential Revision: https://reviews.llvm.org/D91675
2020-12-14 15:39:06 +08:00
; CHECK-P8-NEXT: bl sqrtf128
[NFC][Test] Update test for IEEE Long Double
2020-11-20 17:56:53 +08:00
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: mtlr r0
; CHECK-P8-NEXT: blr
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
%res = call fp128 @llvm.experimental.constrained.sqrt.f128(
fp128 %f1,
metadata !"round.dynamic",
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
metadata !"fpexcept.strict") #0
[PowerPC] Add fma/fsqrt/fmax strict-fp intrinsics This patch adds strict-fp intrinsics support for fma, fsqrt, fmaxnum and fminnum on PowerPC. Reviewed By: hfinkel Differential Revision: https://reviews.llvm.org/D72749
2020-05-12 13:40:54 +08:00
ret fp128 %res
}
Fix errors in use of strictfp attribute. Errors spotted with use of: https://reviews.llvm.org/D68233
2020-05-30 00:15:54 +08:00
attributes #0 = { strictfp }