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
22 lines
1.8 KiB
LLVM
22 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output < %s | FileCheck %s
|
|
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
define void @test1() {
|
|
; CHECK-LABEL: 'test1'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call double asm "rsqrt.approx.ftz.f64 $0, $1;", "=d,d"(double 1.000000e+00)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call { i32, i32 } asm "{\0A\09mad.lo.cc.u32 $0, $2, $3, $4;\0A\09madc.hi.u32 $1, $2, $3, 0;\0A\09}", "=r,=r,r,r,r"(i32 2, i32 3, i32 3)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call i32 asm sideeffect "{ \0A\09.reg .pred \09%p1; \0A\09setp.ne.u32 \09%p1, $1, 0; \0A\09vote.ballot.b32 \09$0, %p1; \0A\09}", "=r,r"(i32 0)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call i32 asm sideeffect "{ \0A\09.reg .pred \09%p1; \0A\09setp.ne.u32 \09%p1, $1, 0; \0A\09@%p1 exit; \0A\09}", "=r,r"(i32 0)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void asm sideeffect ".pragma \22nounroll\22;\0A\09", "~{memory}"()
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
|
|
;
|
|
%1 = call double asm "rsqrt.approx.ftz.f64 $0, $1;", "=d,d"(double 1.0)
|
|
%2 = call { i32, i32 } asm "{\0A\09mad.lo.cc.u32 $0, $2, $3, $4;\0A\09madc.hi.u32 $1, $2, $3, 0;\0A\09}", "=r,=r,r,r,r"(i32 2, i32 3, i32 3)
|
|
%3 = call i32 asm sideeffect "{ \0A\09.reg .pred \09%p1; \0A\09setp.ne.u32 \09%p1, $1, 0; \0A\09vote.ballot.b32 \09$0, %p1; \0A\09}", "=r,r"(i32 0)
|
|
%4 = call i32 asm sideeffect "{ \0A\09.reg .pred \09%p1; \0A\09setp.ne.u32 \09%p1, $1, 0; \0A\09@%p1 exit; \0A\09}", "=r,r"(i32 0)
|
|
call void asm sideeffect ".pragma \22nounroll\22;\0A\09", "~{memory}"()
|
|
ret void
|
|
}
|