[llvm-branch-commits] [llvm] [AMDGPU][RegBankCombiner] Add cast_of_cast and constant_fold_cast combines (PR #131307)
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Fri Mar 14 04:19:24 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Pierre van Houtryve (Pierre-vh)
<details>
<summary>Changes</summary>
We can add a bunch of exts/truncs during RBSelect, we should be able to fold
them away afterwards.
---
Patch is 184.40 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/131307.diff
8 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPUCombine.td (+2-1)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll (+217-397)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/fshr.ll (+256-424)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/saddsat.ll (+120-131)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/shl-ext-reduce.ll (+5-21)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/ssubsat.ll (+146-157)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.is.fpclass.f16.ll (-1)
- (modified) llvm/test/CodeGen/AMDGPU/v_sat_pk_u8_i16.ll (+22-32)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
index 36653867fbba0..a21505356274b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
@@ -180,5 +180,6 @@ def AMDGPURegBankCombiner : GICombiner<
[unmerge_merge, unmerge_cst, unmerge_undef,
zext_trunc_fold, int_minmax_to_med3, ptr_add_immed_chain,
fp_minmax_to_clamp, fp_minmax_to_med3, fmed3_intrinsic_to_clamp,
- identity_combines, redundant_and]> {
+ identity_combines, redundant_and, constant_fold_cast_op,
+ cast_of_cast_combines]> {
}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll
index 3a52497bd6e91..07fcb02d98649 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/fshl.ll
@@ -41,10 +41,9 @@ define amdgpu_ps i7 @s_fshl_i7(i7 inreg %lhs, i7 inreg %rhs, i7 inreg %amt) {
; GFX8-NEXT: v_rcp_iflag_f32_e32 v0, v0
; GFX8-NEXT: s_and_b32 s2, s2, 0x7f
; GFX8-NEXT: s_and_b32 s1, s1, 0x7f
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
+; GFX8-NEXT: s_lshr_b32 s1, s1, 1
; GFX8-NEXT: v_mul_f32_e32 v0, 0x4f7ffffe, v0
; GFX8-NEXT: v_cvt_u32_f32_e32 v0, v0
-; GFX8-NEXT: s_lshr_b32 s1, s1, 1
; GFX8-NEXT: v_mul_lo_u32 v1, v0, -7
; GFX8-NEXT: v_mul_hi_u32 v1, v0, v1
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v1
@@ -72,10 +71,9 @@ define amdgpu_ps i7 @s_fshl_i7(i7 inreg %lhs, i7 inreg %rhs, i7 inreg %amt) {
; GFX9-NEXT: v_rcp_iflag_f32_e32 v0, v0
; GFX9-NEXT: s_and_b32 s2, s2, 0x7f
; GFX9-NEXT: s_and_b32 s1, s1, 0x7f
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
+; GFX9-NEXT: s_lshr_b32 s1, s1, 1
; GFX9-NEXT: v_mul_f32_e32 v0, 0x4f7ffffe, v0
; GFX9-NEXT: v_cvt_u32_f32_e32 v0, v0
-; GFX9-NEXT: s_lshr_b32 s1, s1, 1
; GFX9-NEXT: v_mul_lo_u32 v1, v0, -7
; GFX9-NEXT: v_mul_hi_u32 v1, v0, v1
; GFX9-NEXT: v_add_u32_e32 v0, v0, v1
@@ -102,9 +100,8 @@ define amdgpu_ps i7 @s_fshl_i7(i7 inreg %lhs, i7 inreg %rhs, i7 inreg %amt) {
; GFX10-NEXT: v_cvt_f32_ubyte0_e32 v0, 7
; GFX10-NEXT: s_and_b32 s2, s2, 0x7f
; GFX10-NEXT: s_and_b32 s1, s1, 0x7f
-; GFX10-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX10-NEXT: v_rcp_iflag_f32_e32 v0, v0
; GFX10-NEXT: s_lshr_b32 s1, s1, 1
+; GFX10-NEXT: v_rcp_iflag_f32_e32 v0, v0
; GFX10-NEXT: v_mul_f32_e32 v0, 0x4f7ffffe, v0
; GFX10-NEXT: v_cvt_u32_f32_e32 v0, v0
; GFX10-NEXT: v_mul_lo_u32 v1, v0, -7
@@ -134,9 +131,8 @@ define amdgpu_ps i7 @s_fshl_i7(i7 inreg %lhs, i7 inreg %rhs, i7 inreg %amt) {
; GFX11-NEXT: s_and_b32 s2, s2, 0x7f
; GFX11-NEXT: s_and_b32 s1, s1, 0x7f
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX11-NEXT: v_rcp_iflag_f32_e32 v0, v0
; GFX11-NEXT: s_lshr_b32 s1, s1, 1
+; GFX11-NEXT: v_rcp_iflag_f32_e32 v0, v0
; GFX11-NEXT: s_waitcnt_depctr 0xfff
; GFX11-NEXT: v_mul_f32_e32 v0, 0x4f7ffffe, v0
; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
@@ -351,11 +347,8 @@ define amdgpu_ps i8 @s_fshl_i8(i8 inreg %lhs, i8 inreg %rhs, i8 inreg %amt) {
; GFX8: ; %bb.0:
; GFX8-NEXT: s_and_b32 s1, s1, 0xff
; GFX8-NEXT: s_and_b32 s3, s2, 7
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX8-NEXT: s_andn2_b32 s2, 7, s2
-; GFX8-NEXT: s_and_b32 s3, 0xffff, s3
; GFX8-NEXT: s_lshr_b32 s1, s1, 1
-; GFX8-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX8-NEXT: s_andn2_b32 s2, 7, s2
; GFX8-NEXT: s_lshl_b32 s0, s0, s3
; GFX8-NEXT: s_lshr_b32 s1, s1, s2
; GFX8-NEXT: s_or_b32 s0, s0, s1
@@ -365,11 +358,8 @@ define amdgpu_ps i8 @s_fshl_i8(i8 inreg %lhs, i8 inreg %rhs, i8 inreg %amt) {
; GFX9: ; %bb.0:
; GFX9-NEXT: s_and_b32 s1, s1, 0xff
; GFX9-NEXT: s_and_b32 s3, s2, 7
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX9-NEXT: s_andn2_b32 s2, 7, s2
-; GFX9-NEXT: s_and_b32 s3, 0xffff, s3
; GFX9-NEXT: s_lshr_b32 s1, s1, 1
-; GFX9-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX9-NEXT: s_andn2_b32 s2, 7, s2
; GFX9-NEXT: s_lshl_b32 s0, s0, s3
; GFX9-NEXT: s_lshr_b32 s1, s1, s2
; GFX9-NEXT: s_or_b32 s0, s0, s1
@@ -379,11 +369,8 @@ define amdgpu_ps i8 @s_fshl_i8(i8 inreg %lhs, i8 inreg %rhs, i8 inreg %amt) {
; GFX10: ; %bb.0:
; GFX10-NEXT: s_and_b32 s1, s1, 0xff
; GFX10-NEXT: s_and_b32 s3, s2, 7
-; GFX10-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX10-NEXT: s_andn2_b32 s2, 7, s2
-; GFX10-NEXT: s_and_b32 s3, 0xffff, s3
; GFX10-NEXT: s_lshr_b32 s1, s1, 1
-; GFX10-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX10-NEXT: s_andn2_b32 s2, 7, s2
; GFX10-NEXT: s_lshl_b32 s0, s0, s3
; GFX10-NEXT: s_lshr_b32 s1, s1, s2
; GFX10-NEXT: s_or_b32 s0, s0, s1
@@ -393,11 +380,8 @@ define amdgpu_ps i8 @s_fshl_i8(i8 inreg %lhs, i8 inreg %rhs, i8 inreg %amt) {
; GFX11: ; %bb.0:
; GFX11-NEXT: s_and_b32 s1, s1, 0xff
; GFX11-NEXT: s_and_b32 s3, s2, 7
-; GFX11-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX11-NEXT: s_and_not1_b32 s2, 7, s2
-; GFX11-NEXT: s_and_b32 s3, 0xffff, s3
; GFX11-NEXT: s_lshr_b32 s1, s1, 1
-; GFX11-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX11-NEXT: s_and_not1_b32 s2, 7, s2
; GFX11-NEXT: s_lshl_b32 s0, s0, s3
; GFX11-NEXT: s_lshr_b32 s1, s1, s2
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
@@ -489,7 +473,6 @@ define amdgpu_ps i8 @s_fshl_i8_4(i8 inreg %lhs, i8 inreg %rhs) {
; GFX8-LABEL: s_fshl_i8_4:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_and_b32 s1, s1, 0xff
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
; GFX8-NEXT: s_lshl_b32 s0, s0, 4
; GFX8-NEXT: s_lshr_b32 s1, s1, 4
; GFX8-NEXT: s_or_b32 s0, s0, s1
@@ -498,7 +481,6 @@ define amdgpu_ps i8 @s_fshl_i8_4(i8 inreg %lhs, i8 inreg %rhs) {
; GFX9-LABEL: s_fshl_i8_4:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_and_b32 s1, s1, 0xff
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
; GFX9-NEXT: s_lshl_b32 s0, s0, 4
; GFX9-NEXT: s_lshr_b32 s1, s1, 4
; GFX9-NEXT: s_or_b32 s0, s0, s1
@@ -508,7 +490,6 @@ define amdgpu_ps i8 @s_fshl_i8_4(i8 inreg %lhs, i8 inreg %rhs) {
; GFX10: ; %bb.0:
; GFX10-NEXT: s_and_b32 s1, s1, 0xff
; GFX10-NEXT: s_lshl_b32 s0, s0, 4
-; GFX10-NEXT: s_and_b32 s1, 0xffff, s1
; GFX10-NEXT: s_lshr_b32 s1, s1, 4
; GFX10-NEXT: s_or_b32 s0, s0, s1
; GFX10-NEXT: ; return to shader part epilog
@@ -517,9 +498,8 @@ define amdgpu_ps i8 @s_fshl_i8_4(i8 inreg %lhs, i8 inreg %rhs) {
; GFX11: ; %bb.0:
; GFX11-NEXT: s_and_b32 s1, s1, 0xff
; GFX11-NEXT: s_lshl_b32 s0, s0, 4
-; GFX11-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GFX11-NEXT: s_lshr_b32 s1, s1, 4
+; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; GFX11-NEXT: s_or_b32 s0, s0, s1
; GFX11-NEXT: ; return to shader part epilog
%result = call i8 @llvm.fshl.i8(i8 %lhs, i8 %rhs, i8 4)
@@ -586,7 +566,6 @@ define amdgpu_ps i8 @s_fshl_i8_5(i8 inreg %lhs, i8 inreg %rhs) {
; GFX8-LABEL: s_fshl_i8_5:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_and_b32 s1, s1, 0xff
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
; GFX8-NEXT: s_lshl_b32 s0, s0, 5
; GFX8-NEXT: s_lshr_b32 s1, s1, 3
; GFX8-NEXT: s_or_b32 s0, s0, s1
@@ -595,7 +574,6 @@ define amdgpu_ps i8 @s_fshl_i8_5(i8 inreg %lhs, i8 inreg %rhs) {
; GFX9-LABEL: s_fshl_i8_5:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_and_b32 s1, s1, 0xff
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
; GFX9-NEXT: s_lshl_b32 s0, s0, 5
; GFX9-NEXT: s_lshr_b32 s1, s1, 3
; GFX9-NEXT: s_or_b32 s0, s0, s1
@@ -605,7 +583,6 @@ define amdgpu_ps i8 @s_fshl_i8_5(i8 inreg %lhs, i8 inreg %rhs) {
; GFX10: ; %bb.0:
; GFX10-NEXT: s_and_b32 s1, s1, 0xff
; GFX10-NEXT: s_lshl_b32 s0, s0, 5
-; GFX10-NEXT: s_and_b32 s1, 0xffff, s1
; GFX10-NEXT: s_lshr_b32 s1, s1, 3
; GFX10-NEXT: s_or_b32 s0, s0, s1
; GFX10-NEXT: ; return to shader part epilog
@@ -614,9 +591,8 @@ define amdgpu_ps i8 @s_fshl_i8_5(i8 inreg %lhs, i8 inreg %rhs) {
; GFX11: ; %bb.0:
; GFX11-NEXT: s_and_b32 s1, s1, 0xff
; GFX11-NEXT: s_lshl_b32 s0, s0, 5
-; GFX11-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GFX11-NEXT: s_lshr_b32 s1, s1, 3
+; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; GFX11-NEXT: s_or_b32 s0, s0, s1
; GFX11-NEXT: ; return to shader part epilog
%result = call i8 @llvm.fshl.i8(i8 %lhs, i8 %rhs, i8 5)
@@ -702,23 +678,17 @@ define amdgpu_ps i16 @s_fshl_v2i8(i16 inreg %lhs.arg, i16 inreg %rhs.arg, i16 in
; GFX8-NEXT: s_and_b32 s1, s1, 0xff
; GFX8-NEXT: s_lshr_b32 s5, s2, 8
; GFX8-NEXT: s_and_b32 s6, s2, 7
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX8-NEXT: s_andn2_b32 s2, 7, s2
-; GFX8-NEXT: s_and_b32 s6, 0xffff, s6
; GFX8-NEXT: s_lshr_b32 s1, s1, 1
-; GFX8-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX8-NEXT: s_andn2_b32 s2, 7, s2
; GFX8-NEXT: s_lshr_b32 s3, s0, 8
; GFX8-NEXT: s_lshl_b32 s0, s0, s6
; GFX8-NEXT: s_lshr_b32 s1, s1, s2
; GFX8-NEXT: s_or_b32 s0, s0, s1
; GFX8-NEXT: s_and_b32 s1, s5, 7
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
; GFX8-NEXT: s_and_b32 s2, s4, 0xff
; GFX8-NEXT: s_lshl_b32 s1, s3, s1
-; GFX8-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX8-NEXT: s_andn2_b32 s3, 7, s5
; GFX8-NEXT: s_lshr_b32 s2, s2, 1
-; GFX8-NEXT: s_and_b32 s3, 0xffff, s3
+; GFX8-NEXT: s_andn2_b32 s3, 7, s5
; GFX8-NEXT: s_lshr_b32 s2, s2, s3
; GFX8-NEXT: s_or_b32 s1, s1, s2
; GFX8-NEXT: s_and_b32 s1, s1, 0xff
@@ -733,23 +703,17 @@ define amdgpu_ps i16 @s_fshl_v2i8(i16 inreg %lhs.arg, i16 inreg %rhs.arg, i16 in
; GFX9-NEXT: s_and_b32 s1, s1, 0xff
; GFX9-NEXT: s_lshr_b32 s5, s2, 8
; GFX9-NEXT: s_and_b32 s6, s2, 7
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX9-NEXT: s_andn2_b32 s2, 7, s2
-; GFX9-NEXT: s_and_b32 s6, 0xffff, s6
; GFX9-NEXT: s_lshr_b32 s1, s1, 1
-; GFX9-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX9-NEXT: s_andn2_b32 s2, 7, s2
; GFX9-NEXT: s_lshr_b32 s3, s0, 8
; GFX9-NEXT: s_lshl_b32 s0, s0, s6
; GFX9-NEXT: s_lshr_b32 s1, s1, s2
; GFX9-NEXT: s_or_b32 s0, s0, s1
; GFX9-NEXT: s_and_b32 s1, s5, 7
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
; GFX9-NEXT: s_and_b32 s2, s4, 0xff
; GFX9-NEXT: s_lshl_b32 s1, s3, s1
-; GFX9-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX9-NEXT: s_andn2_b32 s3, 7, s5
; GFX9-NEXT: s_lshr_b32 s2, s2, 1
-; GFX9-NEXT: s_and_b32 s3, 0xffff, s3
+; GFX9-NEXT: s_andn2_b32 s3, 7, s5
; GFX9-NEXT: s_lshr_b32 s2, s2, s3
; GFX9-NEXT: s_or_b32 s1, s1, s2
; GFX9-NEXT: s_and_b32 s1, s1, 0xff
@@ -761,25 +725,19 @@ define amdgpu_ps i16 @s_fshl_v2i8(i16 inreg %lhs.arg, i16 inreg %rhs.arg, i16 in
; GFX10-LABEL: s_fshl_v2i8:
; GFX10: ; %bb.0:
; GFX10-NEXT: s_lshr_b32 s4, s1, 8
-; GFX10-NEXT: s_and_b32 s5, s2, 7
-; GFX10-NEXT: s_lshr_b32 s6, s2, 8
-; GFX10-NEXT: s_and_b32 s5, 0xffff, s5
+; GFX10-NEXT: s_lshr_b32 s5, s2, 8
+; GFX10-NEXT: s_and_b32 s6, s2, 7
; GFX10-NEXT: s_and_b32 s4, s4, 0xff
; GFX10-NEXT: s_lshr_b32 s3, s0, 8
; GFX10-NEXT: s_and_b32 s1, s1, 0xff
-; GFX10-NEXT: s_lshl_b32 s0, s0, s5
-; GFX10-NEXT: s_and_b32 s5, s6, 7
-; GFX10-NEXT: s_and_b32 s4, 0xffff, s4
-; GFX10-NEXT: s_andn2_b32 s6, 7, s6
-; GFX10-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX10-NEXT: s_andn2_b32 s2, 7, s2
-; GFX10-NEXT: s_and_b32 s5, 0xffff, s5
+; GFX10-NEXT: s_lshl_b32 s0, s0, s6
+; GFX10-NEXT: s_and_b32 s6, s5, 7
; GFX10-NEXT: s_lshr_b32 s4, s4, 1
-; GFX10-NEXT: s_and_b32 s6, 0xffff, s6
+; GFX10-NEXT: s_andn2_b32 s5, 7, s5
; GFX10-NEXT: s_lshr_b32 s1, s1, 1
-; GFX10-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX10-NEXT: s_lshl_b32 s3, s3, s5
-; GFX10-NEXT: s_lshr_b32 s4, s4, s6
+; GFX10-NEXT: s_andn2_b32 s2, 7, s2
+; GFX10-NEXT: s_lshl_b32 s3, s3, s6
+; GFX10-NEXT: s_lshr_b32 s4, s4, s5
; GFX10-NEXT: s_lshr_b32 s1, s1, s2
; GFX10-NEXT: s_or_b32 s2, s3, s4
; GFX10-NEXT: s_or_b32 s0, s0, s1
@@ -792,25 +750,19 @@ define amdgpu_ps i16 @s_fshl_v2i8(i16 inreg %lhs.arg, i16 inreg %rhs.arg, i16 in
; GFX11-LABEL: s_fshl_v2i8:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_lshr_b32 s4, s1, 8
-; GFX11-NEXT: s_and_b32 s5, s2, 7
-; GFX11-NEXT: s_lshr_b32 s6, s2, 8
-; GFX11-NEXT: s_and_b32 s5, 0xffff, s5
+; GFX11-NEXT: s_lshr_b32 s5, s2, 8
+; GFX11-NEXT: s_and_b32 s6, s2, 7
; GFX11-NEXT: s_and_b32 s4, s4, 0xff
; GFX11-NEXT: s_lshr_b32 s3, s0, 8
; GFX11-NEXT: s_and_b32 s1, s1, 0xff
-; GFX11-NEXT: s_lshl_b32 s0, s0, s5
-; GFX11-NEXT: s_and_b32 s5, s6, 7
-; GFX11-NEXT: s_and_b32 s4, 0xffff, s4
-; GFX11-NEXT: s_and_not1_b32 s6, 7, s6
-; GFX11-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX11-NEXT: s_and_not1_b32 s2, 7, s2
-; GFX11-NEXT: s_and_b32 s5, 0xffff, s5
+; GFX11-NEXT: s_lshl_b32 s0, s0, s6
+; GFX11-NEXT: s_and_b32 s6, s5, 7
; GFX11-NEXT: s_lshr_b32 s4, s4, 1
-; GFX11-NEXT: s_and_b32 s6, 0xffff, s6
+; GFX11-NEXT: s_and_not1_b32 s5, 7, s5
; GFX11-NEXT: s_lshr_b32 s1, s1, 1
-; GFX11-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX11-NEXT: s_lshl_b32 s3, s3, s5
-; GFX11-NEXT: s_lshr_b32 s4, s4, s6
+; GFX11-NEXT: s_and_not1_b32 s2, 7, s2
+; GFX11-NEXT: s_lshl_b32 s3, s3, s6
+; GFX11-NEXT: s_lshr_b32 s4, s4, s5
; GFX11-NEXT: s_lshr_b32 s1, s1, s2
; GFX11-NEXT: s_or_b32 s2, s3, s4
; GFX11-NEXT: s_or_b32 s0, s0, s1
@@ -1030,11 +982,8 @@ define amdgpu_ps i32 @s_fshl_v4i8(i32 inreg %lhs.arg, i32 inreg %rhs.arg, i32 in
; GFX8-NEXT: s_lshr_b32 s10, s2, 16
; GFX8-NEXT: s_lshr_b32 s11, s2, 24
; GFX8-NEXT: s_and_b32 s12, s2, 7
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX8-NEXT: s_andn2_b32 s2, 7, s2
-; GFX8-NEXT: s_and_b32 s12, 0xffff, s12
; GFX8-NEXT: s_lshr_b32 s1, s1, 1
-; GFX8-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX8-NEXT: s_andn2_b32 s2, 7, s2
; GFX8-NEXT: s_lshr_b32 s3, s0, 8
; GFX8-NEXT: s_lshr_b32 s4, s0, 16
; GFX8-NEXT: s_lshr_b32 s5, s0, 24
@@ -1042,29 +991,24 @@ define amdgpu_ps i32 @s_fshl_v4i8(i32 inreg %lhs.arg, i32 inreg %rhs.arg, i32 in
; GFX8-NEXT: s_lshr_b32 s1, s1, s2
; GFX8-NEXT: s_or_b32 s0, s0, s1
; GFX8-NEXT: s_and_b32 s1, s9, 7
-; GFX8-NEXT: s_and_b32 s1, 0xffff, s1
; GFX8-NEXT: s_and_b32 s2, s6, 0xff
; GFX8-NEXT: s_lshl_b32 s1, s3, s1
-; GFX8-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX8-NEXT: s_andn2_b32 s3, 7, s9
; GFX8-NEXT: s_lshr_b32 s2, s2, 1
-; GFX8-NEXT: s_and_b32 s3, 0xffff, s3
+; GFX8-NEXT: s_andn2_b32 s3, 7, s9
; GFX8-NEXT: s_lshr_b32 s2, s2, s3
; GFX8-NEXT: s_or_b32 s1, s1, s2
; GFX8-NEXT: s_and_b32 s2, s10, 7
-; GFX8-NEXT: s_lshl_b32 s2, s4, s2
; GFX8-NEXT: s_and_b32 s3, s7, 0xff
-; GFX8-NEXT: s_andn2_b32 s4, 7, s10
+; GFX8-NEXT: s_lshl_b32 s2, s4, s2
; GFX8-NEXT: s_lshr_b32 s3, s3, 1
-; GFX8-NEXT: s_and_b32 s4, 0xffff, s4
+; GFX8-NEXT: s_andn2_b32 s4, 7, s10
; GFX8-NEXT: s_lshr_b32 s3, s3, s4
; GFX8-NEXT: s_or_b32 s2, s2, s3
; GFX8-NEXT: s_and_b32 s3, s11, 7
-; GFX8-NEXT: s_lshl_b32 s3, s5, s3
-; GFX8-NEXT: s_andn2_b32 s5, 7, s11
; GFX8-NEXT: s_and_b32 s1, s1, 0xff
+; GFX8-NEXT: s_lshl_b32 s3, s5, s3
; GFX8-NEXT: s_lshr_b32 s4, s8, 1
-; GFX8-NEXT: s_and_b32 s5, 0xffff, s5
+; GFX8-NEXT: s_andn2_b32 s5, 7, s11
; GFX8-NEXT: s_and_b32 s0, s0, 0xff
; GFX8-NEXT: s_lshl_b32 s1, s1, 8
; GFX8-NEXT: s_lshr_b32 s4, s4, s5
@@ -1088,11 +1032,8 @@ define amdgpu_ps i32 @s_fshl_v4i8(i32 inreg %lhs.arg, i32 inreg %rhs.arg, i32 in
; GFX9-NEXT: s_lshr_b32 s10, s2, 16
; GFX9-NEXT: s_lshr_b32 s11, s2, 24
; GFX9-NEXT: s_and_b32 s12, s2, 7
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX9-NEXT: s_andn2_b32 s2, 7, s2
-; GFX9-NEXT: s_and_b32 s12, 0xffff, s12
; GFX9-NEXT: s_lshr_b32 s1, s1, 1
-; GFX9-NEXT: s_and_b32 s2, 0xffff, s2
+; GFX9-NEXT: s_andn2_b32 s2, 7, s2
; GFX9-NEXT: s_lshr_b32 s3, s0, 8
; GFX9-NEXT: s_lshr_b32 s4, s0, 16
; GFX9-NEXT: s_lshr_b32 s5, s0, 24
@@ -1100,29 +1041,24 @@ define amdgpu_ps i32 @s_fshl_v4i8(i32 inreg %lhs.arg, i32 inreg %rhs.arg, i32 in
; GFX9-NEXT: s_lshr_b32 s1, s1, s2
; GFX9-NEXT: s_or_b32 s0, s0, s1
; GFX9-NEXT: s_and_b32 s1, s9, 7
-; GFX9-NEXT: s_and_b32 s1, 0xffff, s1
; GFX9-NEXT: s_and_b32 s2, s6, 0xff
; GFX9-NEXT: s_lshl_b32 s1, s3, s1
-; GFX9-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX9-NEXT: s_andn2_b32 s3, 7, s9
; GFX9-NEXT: s_lshr_b32 s2, s2, 1
-; GFX9-NEXT: s_and_b32 s3, 0xffff, s3
+; GFX9-NEXT: s_andn2_b32 s3, 7, s9
; GFX9-NEXT: s_lshr_b32 s2, s2, s3
; GFX9-NEXT: s_or_b32 s1, s1, s2
; GFX9-NEXT: s_and_b32 s2, s10, 7
-; GFX9-NEXT: s_lshl_b32 s2, s4, s2
; GFX9-NEXT: s_and_b32 s3, s7, 0xff
-; GFX9-NEXT: s_andn2_b32 s4, 7, s10
+; GFX9-NEXT: s_lshl_b32 s2, s4, s2
; GFX9-NEXT: s_lshr_b32 s3, s3, 1
-; GFX9-NEXT: s_and_b32 s4, 0xffff, s4
+; GFX9-NEXT: s_andn2_b32 s4, 7, s10
; GFX9-NEXT: s_lshr_b32 s3, s3, s4
; GFX9-NEXT: s_or_b32 s2, s2, s3
; GFX9-NEXT: s_and_b32 s3, s11, 7
-; GFX9-NEXT: s_lshl_b32 s3, s5, s3
-; GFX9-NEXT: s_andn2_b32 s5, 7, s11
; GFX9-NEXT: s_and_b32 s1, s1, 0xff
+; GFX9-NEXT: s_lshl_b32 s3, s5, s3
; GFX9-NEXT: s_lshr_b32 s4, s8, 1
-; GFX9-NEXT: s_and_b32 s5, 0xffff, s5
+; GFX9-NEXT: s_andn2_b32 s5, 7, s11
; GFX9-NEXT: s_and_b32 s0, s0, 0xff
; GFX9-NEXT: s_lshl_b32 s1, s1, 8
; GFX9-NEXT: s_lshr_b32 s4, s4, s5
@@ -1146,41 +1082,33 @@ define amdgpu_ps i32 @s_fshl_v4i8(i32 inreg %lhs.arg, i32 inreg %rhs.arg, i32 in
; GFX10-NEXT: s_lshr_b32 s10, s2, 16
; GFX10-NEXT: s_lshr_b32 s11, s2, 24
; GFX10-NEXT: s_and_b32 s12, s2, 7
-; GFX10-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX10-NEXT: s_andn2_b32 s2, 7, s2
; GFX10-NEXT: s_lshr_b32 s1, s1, 1
-; GFX10-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX10-NEXT: s_and_b32 s6, s6, 0xff
+; GFX10-NEXT: s_andn2_b32 s2, 7, s2
+; GFX10-NEXT: s_lshr_b32 s3, s0, 8
; GFX10-NEXT: s_lshr_b32 s1, s1, s2
-; GFX10-NEXT: s_and_b32 s2, s9, 7
-; GFX10-NEXT: s_and_b32 s6, 0xffff, s6
+; GFX10-NEXT: s_and_b32 s2, s6, 0xff
+; GFX10-NEXT: s_and_b32 s6, s9, 7
+; GFX10-NEXT: s_lshr_b32 s2, s2, 1
; GFX10-NEXT: s_andn2_b32 s9, 7, s9
-; GFX10-NEXT: s_lshr_b32 s3, s0, 8
-; GFX10-NEXT: s_and_b32 s12, 0xffff, s12
-; GFX10-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX10-NEXT: s_lshr_b32 s6, s6, 1
-; GFX10-NEXT: s_and_b32 s9, 0xffff, s9
; GFX10-NEXT: s_lshr_b32 s4, s0, 16
; GFX10-NEXT: s_lshr_b32 s5, s0, 24
; GFX10-NEXT: s_lshl_b32 s0, s0, s12
-; GFX10-NEXT: s_lshl_b32 s2, s3, s2
-; GFX10-NEXT: s_lshr_b32 s3, s6, s9
+; GFX10-NEXT: s_lshl_b32 s3, s3, s6
+; GFX10-NEXT: s_lshr_b32 s2, s2, s9
; GFX10-NEXT: s_or_b32 s0, s0, s1
-; GFX10-NEXT: s_or_b32 s1, s2, s3
-; GFX10-NEXT: s_and_b32 s3, s7, 0xff
+; GFX10-NEXT: s_or_b32 s1, s3, s2
+; GFX10-NEXT: s_and_b32 s2, s7, 0xff
+; GFX10-NEXT: s_and_b32 s3, s10, 7
+; GFX10-NEXT: s_lshr_b32 s2, s2, 1
; GFX10-NEXT: s_andn2_b32 s6, 7, s10
-; GFX10-NEXT: s_lshr_b32 s3, s3, 1
-; GFX10-NEXT: s_and_b32 s6, 0xffff, s6
-; GFX10-NEXT: s_and_b32 s2, s10, 7
-; GFX10-NEXT: s_lshr_b32 s3, s3, s6
-; GFX10-NEXT: s_andn2_b32 s6, 7, s11
-; GFX10-NEXT: s_lshl_b32 s2, s4, s2
+; GFX10-NEXT: s_lshl_b32 s3, s4, s3
+; GFX10-NEXT: s_lshr_b32 s2, s2, s6
; GFX10-NEXT: s_and_b32 s4, s11, 7
-; GFX10-NEXT: s_lshr_b32 s7, s8, 1
-; GFX10-NEXT: s_and_b32 s6, 0xffff, s6
+; GFX10-NEXT: s_lshr_b32 s6, s8, 1
+; GFX10-NEXT: s_andn2_b32 s7, 7, s11
; GFX10-NEXT: s_lshl_b32 s4, s5, s4
-; GFX10-NEXT: s_lshr_b32 s5, s7, s6
-; GFX10-NEXT: s_or_b32 s2, s2, s3
+; GFX10-NEXT: s_lshr_b32 s5, s6, s7
+; GFX10-NEXT: s_or_b32 s2, s3, s2
; GFX10-NEXT: s_and_b32 s1, s1, 0xff
; GFX10-NEXT: s_or_b32 s3, s4, s5
; GFX10-NEXT: s_and_b32 s0, s0, 0xff
@@ -1204,41 +1132,33 @@ define amdgpu_ps i32 @s_fshl_v4i8(i32 inreg %lhs.arg, i32 inreg %rhs.arg, i32 in
; GFX11-NEXT: s_lshr_b32 s10, s2, 16
; GFX11-NEXT: s_lshr_b32 s11, s2, 24
; GFX11-NEXT: s_and_b32 s12, s2, 7
-; GFX11-NEXT: s_and_b32 s1, 0xffff, s1
-; GFX11-NEXT: s_and_not1_b32 s2, 7, s2
; GFX11-NEXT: s_lshr_b32 s1, s1, 1
-; GFX11-NEXT: s_and_b32 s2, 0xffff, s2
-; GFX11-NEXT: s_and_b32 s6, s6, 0xff
+; GFX11-NEXT: s_an...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/131307
More information about the llvm-branch-commits
mailing list