derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
54 lines
1.9 KiB
LLVM
54 lines
1.9 KiB
LLVM
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck %s \
|
|
; RUN: --check-prefix=CHECK-ITIN
|
|
; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s \
|
|
; RUN: --check-prefix=CHECK-ITIN
|
|
; RUN: llc -verify-machineinstrs -mcpu=pwr7 -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck %s \
|
|
; RUN: --check-prefix=CHECK-ITIN
|
|
|
|
define void @bn_mul_comba8(ptr nocapture %r, ptr nocapture readonly %a, ptr nocapture readonly %b) {
|
|
; CHECK-LABEL: bn_mul_comba8:
|
|
; CHECK: mulhdu
|
|
; CHECK-NEXT: mulld
|
|
; CHECK: mulhdu
|
|
; CHECK: mulld
|
|
; CHECK-NEXT: mulhdu
|
|
|
|
|
|
; CHECK-ITIN-LABEL: bn_mul_comba8:
|
|
; CHECK-ITIN: mulhdu
|
|
; CHECK-ITIN-NEXT: mulld
|
|
; CHECK-ITIN-NEXT: mulhdu
|
|
; CHECK-ITIN: mulld
|
|
; CHECK-ITIN-NEXT: mulhdu
|
|
|
|
%1 = load i64, ptr %a, align 8
|
|
%conv = zext i64 %1 to i128
|
|
%2 = load i64, ptr %b, align 8
|
|
%conv2 = zext i64 %2 to i128
|
|
%mul = mul nuw i128 %conv2, %conv
|
|
%shr = lshr i128 %mul, 64
|
|
%agep = getelementptr inbounds i64, ptr %a, i64 1
|
|
%3 = load i64, ptr %agep, align 8
|
|
%conv14 = zext i64 %3 to i128
|
|
%mul15 = mul nuw i128 %conv14, %conv
|
|
%add17 = add i128 %mul15, %shr
|
|
%shr19 = lshr i128 %add17, 64
|
|
%conv20 = trunc i128 %shr19 to i64
|
|
%bgep = getelementptr inbounds i64, ptr %b, i64 1
|
|
%4 = load i64, ptr %bgep, align 8
|
|
%conv28 = zext i64 %4 to i128
|
|
%mul31 = mul nuw i128 %conv28, %conv2
|
|
%conv32 = and i128 %add17, 18446744073709551615
|
|
%add33 = add i128 %conv32, %mul31
|
|
%shr35 = lshr i128 %add33, 64
|
|
%conv36 = trunc i128 %shr35 to i64
|
|
%add37 = add i64 %conv36, %conv20
|
|
%cmp38 = icmp ult i64 %add37, %conv36
|
|
%conv148 = zext i1 %cmp38 to i64
|
|
store i64 %conv148, ptr %r, align 8
|
|
ret void
|
|
}
|
|
|