Files
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

131 lines
4.5 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -verify-machineinstrs -mcpu=sm_50 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -verify-machineinstrs -mcpu=sm_50 | %ptxas-verify %}
target triple = "nvptx64-nvidia-cuda"
define i32 @test_prmt_basic(i32 %lo, i32 %hi, i32 %selector) {
; CHECK-LABEL: test_prmt_basic(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<5>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_basic_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_basic_param_1];
; CHECK-NEXT: ld.param.b32 %r3, [test_prmt_basic_param_2];
; CHECK-NEXT: prmt.b32 %r4, %r1, %r2, %r3;
; CHECK-NEXT: st.param.b32 [func_retval0], %r4;
; CHECK-NEXT: ret;
%val = call i32 @llvm.nvvm.prmt(i32 %lo, i32 %hi, i32 %selector)
ret i32 %val
}
define i32 @test_prmt_f4e(i32 %lo, i32 %hi, i32 %selector) {
; CHECK-LABEL: test_prmt_f4e(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<5>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_f4e_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_f4e_param_1];
; CHECK-NEXT: ld.param.b32 %r3, [test_prmt_f4e_param_2];
; CHECK-NEXT: prmt.b32.f4e %r4, %r1, %r2, %r3;
; CHECK-NEXT: st.param.b32 [func_retval0], %r4;
; CHECK-NEXT: ret;
%val = call i32 @llvm.nvvm.prmt.f4e(i32 %lo, i32 %hi, i32 %selector)
ret i32 %val
}
define i32 @test_prmt_b4e(i32 %lo, i32 %hi, i32 %selector) {
; CHECK-LABEL: test_prmt_b4e(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<5>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_b4e_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_b4e_param_1];
; CHECK-NEXT: ld.param.b32 %r3, [test_prmt_b4e_param_2];
; CHECK-NEXT: prmt.b32.b4e %r4, %r1, %r2, %r3;
; CHECK-NEXT: st.param.b32 [func_retval0], %r4;
; CHECK-NEXT: ret;
%val = call i32 @llvm.nvvm.prmt.b4e(i32 %lo, i32 %hi, i32 %selector)
ret i32 %val
}
define i32 @test_prmt_rc8(i32 %lo, i32 %selector) {
; CHECK-LABEL: test_prmt_rc8(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<4>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_rc8_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_rc8_param_1];
; CHECK-NEXT: prmt.b32.rc8 %r3, %r1, 0, %r2;
; CHECK-NEXT: st.param.b32 [func_retval0], %r3;
; CHECK-NEXT: ret;
%val = call i32 @llvm.nvvm.prmt.rc8(i32 %lo, i32 %selector)
ret i32 %val
}
define i32 @test_prmt_ecl(i32 %lo, i32 %selector) {
; CHECK-LABEL: test_prmt_ecl(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<4>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_ecl_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_ecl_param_1];
; CHECK-NEXT: prmt.b32.ecl %r3, %r1, 0, %r2;
; CHECK-NEXT: st.param.b32 [func_retval0], %r3;
; CHECK-NEXT: ret;
%val = call i32 @llvm.nvvm.prmt.ecl(i32 %lo, i32 %selector)
ret i32 %val
}
define i32 @test_prmt_ecr(i32 %lo, i32 %selector) {
; CHECK-LABEL: test_prmt_ecr(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<4>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_ecr_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_ecr_param_1];
; CHECK-NEXT: prmt.b32.ecr %r3, %r1, 0, %r2;
; CHECK-NEXT: st.param.b32 [func_retval0], %r3;
; CHECK-NEXT: ret;
%val = call i32 @llvm.nvvm.prmt.ecr(i32 %lo, i32 %selector)
ret i32 %val
}
define i32 @test_prmt_rc16(i32 %lo, i32 %selector) {
; CHECK-LABEL: test_prmt_rc16(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<4>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_rc16_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_rc16_param_1];
; CHECK-NEXT: prmt.b32.rc16 %r3, %r1, 0, %r2;
; CHECK-NEXT: st.param.b32 [func_retval0], %r3;
; CHECK-NEXT: ret;
%val = call i32 @llvm.nvvm.prmt.rc16(i32 %lo, i32 %selector)
ret i32 %val
}
define i32 @test_prmt_f4e_folding(i32 %lo, i32 %hi, i32 %ptr) {
; CHECK-LABEL: test_prmt_f4e_folding(
; CHECK: {
; CHECK-NEXT: .reg .b32 %r<5>;
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b32 %r1, [test_prmt_f4e_folding_param_0];
; CHECK-NEXT: ld.param.b32 %r2, [test_prmt_f4e_folding_param_1];
; CHECK-NEXT: ld.param.b32 %r3, [test_prmt_f4e_folding_param_2];
; CHECK-NEXT: prmt.b32.f4e %r4, %r1, %r2, %r3;
; CHECK-NEXT: st.param.b32 [func_retval0], %r4;
; CHECK-NEXT: ret;
%sh_amt = shl i32 %ptr, 3
%val = call i32 @llvm.fshr.i32(i32 %hi, i32 %lo, i32 %sh_amt)
ret i32 %val
}