Skip to content

[NFC][AMDGPU] Add D16 test for multiple fptrunc image sample #141771

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
harrisonGPU wants to merge 3 commits into from
Closed

[NFC][AMDGPU] Add D16 test for multiple fptrunc image sample #141771

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b2f8b2c
[NFC][AMDGPU] Add a new test for image-d16
harrisonGPU May 28, 2025
62a2e1c
[AMDGPU] Update test.
harrisonGPU Jun 8, 2025
1ca0fa1
[AMDGPU] Update.
harrisonGPU Jun 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 41 additions & 0 deletions llvm/test/Transforms/InstCombine/AMDGPU/image-d16.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
; RUN: opt -mtriple=amdgcn--amdpal -mcpu=gfx810 -S -passes=instcombine %s | FileCheck --check-prefixes=GFX81PLUS %s
; RUN: opt -mtriple=amdgcn--amdpal -mcpu=gfx900 -S -passes=instcombine %s | FileCheck --check-prefixes=GFX81PLUS %s
; RUN: opt -mtriple=amdgcn--amdpal -mcpu=gfx1010 -S -passes=instcombine %s | FileCheck --check-prefixes=GFX81PLUS %s
; RUN: opt -mtriple=amdgcn--amdpal -mcpu=gfx1100 -S -passes=instcombine %s | FileCheck --check-prefixes=GFX81PLUS %s

define amdgpu_ps half @image_sample_2d_fptrunc_to_d16(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s, float %t) {
; GFX7-LABEL: @image_sample_2d_fptrunc_to_d16(
Expand Down Expand Up @@ -121,6 +122,46 @@ main_body:
ret half %addf_sum.2
}

define amdgpu_ps half @image_sample_2d_multi_fptrunc_to_d16(<8 x i32> %surf_desc, <4 x i32> %samp, float %u, float %v) {
; GFX7-LABEL: @image_sample_2d_multi_fptrunc_to_d16(
; GFX7-NEXT: main_body:
; GFX7-NEXT: [[SAMPLE:%.*]] = call <3 x float> @llvm.amdgcn.image.sample.lz.2d.v3f32.f32.v8i32.v4i32(i32 7, float [[U:%.*]], float [[V:%.*]], <8 x i32> [[SURF_DESC:%.*]], <4 x i32> [[SAMP:%.*]], i1 false, i32 0, i32 0)
; GFX7-NEXT: [[E0:%.*]] = extractelement <3 x float> [[SAMPLE]], i64 0
; GFX7-NEXT: [[H0:%.*]] = fptrunc float [[E0]] to half
; GFX7-NEXT: [[E1:%.*]] = extractelement <3 x float> [[SAMPLE]], i64 1
; GFX7-NEXT: [[H1:%.*]] = fptrunc float [[E1]] to half
; GFX7-NEXT: [[E2:%.*]] = extractelement <3 x float> [[SAMPLE]], i64 2
; GFX7-NEXT: [[H2:%.*]] = fptrunc float [[E2]] to half
; GFX7-NEXT: [[MUL:%.*]] = fmul half [[H0]], [[H1]]
; GFX7-NEXT: [[RES:%.*]] = fadd half [[MUL]], [[H2]]
; GFX7-NEXT: ret half [[RES]]
;
; GFX81PLUS-LABEL: @image_sample_2d_multi_fptrunc_to_d16(
; GFX81PLUS-NEXT: main_body:
; GFX81PLUS-NEXT: [[SAMPLE:%.*]] = call <3 x float> @llvm.amdgcn.image.sample.lz.2d.v3f32.f32.v8i32.v4i32(i32 7, float [[U:%.*]], float [[V:%.*]], <8 x i32> [[SURF_DESC:%.*]], <4 x i32> [[SAMP:%.*]], i1 false, i32 0, i32 0)
; GFX81PLUS-NEXT: [[E0:%.*]] = extractelement <3 x float> [[SAMPLE]], i64 0
; GFX81PLUS-NEXT: [[H0:%.*]] = fptrunc float [[E0]] to half
; GFX81PLUS-NEXT: [[E1:%.*]] = extractelement <3 x float> [[SAMPLE]], i64 1
; GFX81PLUS-NEXT: [[H1:%.*]] = fptrunc float [[E1]] to half
; GFX81PLUS-NEXT: [[E2:%.*]] = extractelement <3 x float> [[SAMPLE]], i64 2
; GFX81PLUS-NEXT: [[H2:%.*]] = fptrunc float [[E2]] to half
; GFX81PLUS-NEXT: [[MUL:%.*]] = fmul half [[H0]], [[H1]]
; GFX81PLUS-NEXT: [[RES:%.*]] = fadd half [[MUL]], [[H2]]
; GFX81PLUS-NEXT: ret half [[RES]]
;
main_body:
%sample = call <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f32.v8i32.v4i32(i32 15, float %u, float %v, <8 x i32> %surf_desc, <4 x i32> %samp, i1 false, i32 0, i32 0)
%e0 = extractelement <4 x float> %sample, i32 0
%h0 = fptrunc float %e0 to half
%e1 = extractelement <4 x float> %sample, i32 1
%h1 = fptrunc float %e1 to half
%e2 = extractelement <4 x float> %sample, i32 2
%h2 = fptrunc float %e2 to half
%mul = fmul half %h0, %h1
%res = fadd half %mul, %h2
ret half %res
}

define amdgpu_ps half @image_gather4_2d_v4f32(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t) {
; GFX7-LABEL: @image_gather4_2d_v4f32(
; GFX7-NEXT: main_body:
Expand Down
Loading