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
73 lines
2.4 KiB
LLVM
73 lines
2.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; Test widening vector multiply-and-add on z17.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z17 | FileCheck %s
|
|
|
|
; Test a v2i64 (even) -> i128 unsigned widening multiply-and-add.
|
|
define i128 @f1(<2 x i64> %val1, <2 x i64> %val2, i128 %val3) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vmaleg %v0, %v24, %v26, %v0
|
|
; CHECK-NEXT: vst %v0, 0(%r2), 3
|
|
; CHECK-NEXT: br %r14
|
|
%elt1 = extractelement <2 x i64> %val1, i32 0
|
|
%zext1 = zext i64 %elt1 to i128
|
|
%elt2 = extractelement <2 x i64> %val2, i32 0
|
|
%zext2 = zext i64 %elt2 to i128
|
|
%mul = mul i128 %zext1, %zext2
|
|
%ret = add i128 %mul, %val3
|
|
ret i128 %ret
|
|
}
|
|
|
|
; Test a v2i64 (odd) -> i128 unsigned widening multiply-and-add.
|
|
define i128 @f2(<2 x i64> %val1, <2 x i64> %val2, i128 %val3) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vmalog %v0, %v24, %v26, %v0
|
|
; CHECK-NEXT: vst %v0, 0(%r2), 3
|
|
; CHECK-NEXT: br %r14
|
|
%elt1 = extractelement <2 x i64> %val1, i32 1
|
|
%zext1 = zext i64 %elt1 to i128
|
|
%elt2 = extractelement <2 x i64> %val2, i32 1
|
|
%zext2 = zext i64 %elt2 to i128
|
|
%mul = mul i128 %zext1, %zext2
|
|
%ret = add i128 %mul, %val3
|
|
ret i128 %ret
|
|
}
|
|
|
|
; Test a v2i64 (even) -> i128 signed widening multiply-and-add.
|
|
define i128 @f3(<2 x i64> %val1, <2 x i64> %val2, i128 %val3) {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vmaeg %v0, %v24, %v26, %v0
|
|
; CHECK-NEXT: vst %v0, 0(%r2), 3
|
|
; CHECK-NEXT: br %r14
|
|
%elt1 = extractelement <2 x i64> %val1, i32 0
|
|
%sext1 = sext i64 %elt1 to i128
|
|
%elt2 = extractelement <2 x i64> %val2, i32 0
|
|
%sext2 = sext i64 %elt2 to i128
|
|
%mul = mul i128 %sext1, %sext2
|
|
%ret = add i128 %mul, %val3
|
|
ret i128 %ret
|
|
}
|
|
|
|
; Test a v2i64 (odd) -> i128 signed widening multiply-and-add.
|
|
define i128 @f4(<2 x i64> %val1, <2 x i64> %val2, i128 %val3) {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vl %v0, 0(%r3), 3
|
|
; CHECK-NEXT: vmaog %v0, %v24, %v26, %v0
|
|
; CHECK-NEXT: vst %v0, 0(%r2), 3
|
|
; CHECK-NEXT: br %r14
|
|
%elt1 = extractelement <2 x i64> %val1, i32 1
|
|
%sext1 = sext i64 %elt1 to i128
|
|
%elt2 = extractelement <2 x i64> %val2, i32 1
|
|
%sext2 = sext i64 %elt2 to i128
|
|
%mul = mul i128 %sext1, %sext2
|
|
%ret = add i128 %mul, %val3
|
|
ret i128 %ret
|
|
}
|