shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/clang/test/Frontend/fixed_point_comparisons.c
Mariya Podchishchaeva 9ad72df55c
[clang] Use different memory layout type for _BitInt(N) in LLVM IR (#91364) 
There are two problems with _BitInt prior to this patch:
1. For at least some values of N, we cannot use LLVM's iN for the type
of struct elements, array elements, allocas, global variables, and so
on, because the LLVM layout for that type does not match the high-level
layout of _BitInt(N).
Example: Currently for i128:128 targets correct implementation is
possible either for __int128 or for _BitInt(129+) with lowering to iN,
but not both, since we have now correct implementation of __int128 in
place after a21abc7.
When this happens, opaque [M x i8] types used, where M =
sizeof(_BitInt(N)).
2. LLVM doesn't guarantee any particular extension behavior for integer
types that aren't a multiple of 8. For this reason, all _BitInt types
are now have in-memory representation that is a whole number of bytes.
I.e. for example _BitInt(17) now will have memory layout type i32.

This patch also introduces concept of load/store type and adds an API to
CodeGenTypes that returns the IR type that should be used for load and
store operations. This is particularly useful for the case when a
_BitInt ends up having array of bytes as memory layout type. For
_BitInt(N), let M = sizeof(_BitInt(N)), and let BITS = M * 8. Loads and
stores of iM would both (1) produce far better code from the backends
and (2) be far more optimizable by IR passes than loads and stores of [M
x i8].

Fixes https://github.com/llvm/llvm-project/issues/85139
Fixes https://github.com/llvm/llvm-project/issues/83419

---------

Co-authored-by: John McCall <rjmccall@gmail.com>
2024-07-15 09:40:39 +02:00

379 lines
18 KiB
C
Raw Blame History

// RUN: %clang_cc1 -ffixed-point -triple x86_64-unknown-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefixes=CHECK,UNPADDED
// RUN: %clang_cc1 -ffixed-point -triple x86_64-unknown-linux-gnu -fpadding-on-unsigned-fixed-point -emit-llvm %s -o - | FileCheck %s --check-prefixes=CHECK,PADDED
// Fixed point against other fixed point
_Bool b_eq_true = 2.5hk == 2.5uhk; // CHECK-DAG: @b_eq_true = {{.*}}global i8 1, align 1
_Bool b_eq_false = 2.5hk == 2.4uhk; // CHECK-DAG: @b_eq_false = {{.*}}global i8 0, align 1
_Bool b_ne_true = 2.5hk != 2.4uhk; // CHECK-DAG: @b_ne_true = {{.*}}global i8 1, align 1
_Bool b_ne_false = 2.5hk != 2.5uhk; // CHECK-DAG: @b_ne_false = {{.*}}global i8 0, align 1
_Bool b_lt_true = 2.5hk < 2.75uhk; // CHECK-DAG: @b_lt_true = {{.*}}global i8 1, align 1
_Bool b_lt_false = 2.5hk < 2.5uhk; // CHECK-DAG: @b_lt_false = {{.*}}global i8 0, align 1
_Bool b_le_true = 2.5hk <= 2.75uhk; // CHECK-DAG: @b_le_true = {{.*}}global i8 1, align 1
_Bool b_le_true2 = 2.5hk <= 2.5uhk; // CHECK-DAG: @b_le_true2 = {{.*}}global i8 1, align 1
_Bool b_le_false = 2.5hk <= 2.4uhk; // CHECK-DAG: @b_le_false = {{.*}}global i8 0, align 1
_Bool b_gt_true = 2.75hk > 2.5uhk; // CHECK-DAG: @b_gt_true = {{.*}}global i8 1, align 1
_Bool b_gt_false = 2.75hk > 2.75uhk; // CHECK-DAG: @b_gt_false = {{.*}}global i8 0, align 1
_Bool b_ge_true = 2.75hk >= 2.5uhk; // CHECK-DAG: @b_ge_true = {{.*}}global i8 1, align 1
_Bool b_ge_true2 = 2.75hk >= 2.75uhk; // CHECK-DAG: @b_ge_true2 = {{.*}}global i8 1, align 1
_Bool b_ge_false = 2.5hk >= 2.75uhk; // CHECK-DAG: @b_ge_false = {{.*}}global i8 0, align 1
// Fixed point against int
_Bool b_ieq_true = 2.0hk == 2; // CHECK-DAG: @b_ieq_true = {{.*}}global i8 1, align 1
_Bool b_ieq_false = 2.0hk == 3; // CHECK-DAG: @b_ieq_false = {{.*}}global i8 0, align 1
_Bool b_ine_true = 2.0hk != 3; // CHECK-DAG: @b_ine_true = {{.*}}global i8 1, align 1
_Bool b_ine_false = 2.0hk != 2; // CHECK-DAG: @b_ine_false = {{.*}}global i8 0, align 1
_Bool b_ilt_true = 2.0hk < 3; // CHECK-DAG: @b_ilt_true = {{.*}}global i8 1, align 1
_Bool b_ilt_false = 2.0hk < 2; // CHECK-DAG: @b_ilt_false = {{.*}}global i8 0, align 1
_Bool b_ile_true = 2.0hk <= 3; // CHECK-DAG: @b_ile_true = {{.*}}global i8 1, align 1
_Bool b_ile_true2 = 2.0hk <= 2; // CHECK-DAG: @b_ile_true2 = {{.*}}global i8 1, align 1
_Bool b_ile_false = 2.0hk <= 1; // CHECK-DAG: @b_ile_false = {{.*}}global i8 0, align 1
_Bool b_igt_true = 2.0hk > 1; // CHECK-DAG: @b_igt_true = {{.*}}global i8 1, align 1
_Bool b_igt_false = 2.0hk > 2; // CHECK-DAG: @b_igt_false = {{.*}}global i8 0, align 1
_Bool b_ige_true = 2.0hk >= 1; // CHECK-DAG: @b_ige_true = {{.*}}global i8 1, align 1
_Bool b_ige_true2 = 2.0hk >= 2; // CHECK-DAG: @b_ige_true2 = {{.*}}global i8 1, align 1
_Bool b_ige_false = 2.0hk >= 3; // CHECK-DAG: @b_ige_false = {{.*}}global i8 0, align 1
// Different signage
// Since we can have different precisions, non powers of 2 fractions may have
// different actual values when being compared.
_Bool b_sne_true = 2.6hk != 2.6uhk;
// UNPADDED-DAG: @b_sne_true = {{.*}}global i8 1, align 1
// PADDED-DAG: @b_sne_true = {{.*}}global i8 0, align 1
_Bool b_seq_true = 2.0hk == 2u; // CHECK-DAG: @b_seq_true = {{.*}}global i8 1, align 1
_Bool b_seq_true2 = 2.0uhk == 2; // CHECK-DAG: @b_seq_true2 = {{.*}}global i8 1, align 1
void TestComparisons(void) {
short _Accum sa;
_Accum a;
unsigned short _Accum usa;
unsigned _Accum ua;
// Each of these should be a fixed point conversion followed by the actual
// comparison operation.
sa == a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp eq i32 [[UPSCALE_A]], [[A2]]
sa != a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp ne i32 [[UPSCALE_A]], [[A2]]
sa > a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp sgt i32 [[UPSCALE_A]], [[A2]]
sa >= a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp sge i32 [[UPSCALE_A]], [[A2]]
sa < a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp slt i32 [[UPSCALE_A]], [[A2]]
sa <= a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp sle i32 [[UPSCALE_A]], [[A2]]
usa > ua;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %ua, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp ugt i32 [[UPSCALE_A]], [[A2]]
usa >= ua;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %ua, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp uge i32 [[UPSCALE_A]], [[A2]]
usa < ua;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %ua, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp ult i32 [[UPSCALE_A]], [[A2]]
usa <= ua;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %ua, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp ule i32 [[UPSCALE_A]], [[A2]]
}
void TestIntComparisons(void) {
short _Accum sa;
unsigned short _Accum usa;
int i;
unsigned int ui;
_Bool b;
char c;
short s;
enum E {
A = 2
} e;
// These comparisons shouldn't be that different from comparing against fixed
// point types with other fixed point types.
sa == i;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %i, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// CHECK-NEXT: {{.*}} = icmp eq i39 [[RESIZE_A]], [[UPSCALE_I]]
sa != i;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %i, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// CHECK-NEXT: {{.*}} = icmp ne i39 [[RESIZE_A]], [[UPSCALE_I]]
sa > i;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %i, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// CHECK-NEXT: {{.*}} = icmp sgt i39 [[RESIZE_A]], [[UPSCALE_I]]
sa >= i;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %i, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// CHECK-NEXT: {{.*}} = icmp sge i39 [[RESIZE_A]], [[UPSCALE_I]]
sa < i;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %i, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// CHECK-NEXT: {{.*}} = icmp slt i39 [[RESIZE_A]], [[UPSCALE_I]]
sa <= i;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %i, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i39
// CHECK-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// CHECK-NEXT: {{.*}} = icmp sle i39 [[RESIZE_A]], [[UPSCALE_I]]
usa > ui;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %ui, align 4
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i40
// UNPADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i40
// UNPADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i40 [[RESIZE_I]], 8
// UNPADDED-NEXT: {{.*}} = icmp ugt i40 [[RESIZE_A]], [[UPSCALE_I]]
// PADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i39
// PADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i39
// PADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// PADDED-NEXT: {{.*}} = icmp ugt i39 [[RESIZE_A]], [[UPSCALE_I]]
usa >= ui;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %ui, align 4
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i40
// UNPADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i40
// UNPADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i40 [[RESIZE_I]], 8
// UNPADDED-NEXT: {{.*}} = icmp uge i40 [[RESIZE_A]], [[UPSCALE_I]]
// PADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i39
// PADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i39
// PADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// PADDED-NEXT: {{.*}} = icmp uge i39 [[RESIZE_A]], [[UPSCALE_I]]
usa < ui;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %ui, align 4
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i40
// UNPADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i40
// UNPADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i40 [[RESIZE_I]], 8
// UNPADDED-NEXT: {{.*}} = icmp ult i40 [[RESIZE_A]], [[UPSCALE_I]]
// PADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i39
// PADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i39
// PADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// PADDED-NEXT: {{.*}} = icmp ult i39 [[RESIZE_A]], [[UPSCALE_I]]
usa <= ui;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %ui, align 4
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i40
// UNPADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i40
// UNPADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i40 [[RESIZE_I]], 8
// UNPADDED-NEXT: {{.*}} = icmp ule i40 [[RESIZE_A]], [[UPSCALE_I]]
// PADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i39
// PADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i39
// PADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// PADDED-NEXT: {{.*}} = icmp ule i39 [[RESIZE_A]], [[UPSCALE_I]]
// Allow for comparisons with other int like types. These are no different
// from comparing to an int other than varying sizes. The integer types are
// still converted to ints or unsigned ints from UsualUnaryConversions().
sa == b;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[B:%[0-9]+]] = load i8, ptr %b, align 1
// CHECK-NEXT: %loadedv = trunc i8 [[B]] to i1
// CHECK-NEXT: [[CONV_B:%[a-z0-9]+]] = zext i1 %loadedv to i32
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_B:%[a-z0-9]+]] = sext i32 [[CONV_B]] to i39
// CHECK-NEXT: [[UPSCALE_B:%[a-z0-9]+]] = shl i39 [[RESIZE_B]], 7
// CHECK-NEXT: {{.*}} = icmp eq i39 [[RESIZE_A]], [[UPSCALE_B]]
sa == c;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[C:%[0-9]+]] = load i8, ptr %c, align 1
// CHECK-NEXT: [[CONV_C:%[a-z0-9]+]] = sext i8 [[C]] to i32
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_C:%[a-z0-9]+]] = sext i32 [[CONV_C]] to i39
// CHECK-NEXT: [[UPSCALE_C:%[a-z0-9]+]] = shl i39 [[RESIZE_C]], 7
// CHECK-NEXT: {{.*}} = icmp eq i39 [[RESIZE_A]], [[UPSCALE_C]]
sa == s;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[S:%[0-9]+]] = load i16, ptr %s, align 2
// CHECK-NEXT: [[CONV_S:%[a-z0-9]+]] = sext i16 [[S]] to i32
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i39
// CHECK-NEXT: [[RESIZE_S:%[a-z0-9]+]] = sext i32 [[CONV_S]] to i39
// CHECK-NEXT: [[UPSCALE_S:%[a-z0-9]+]] = shl i39 [[RESIZE_S]], 7
// CHECK-NEXT: {{.*}} = icmp eq i39 [[RESIZE_A]], [[UPSCALE_S]]
// An enum value is IntegralCast to an unsigned int.
usa == e;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %e, align 4
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i40
// UNPADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i40
// UNPADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i40 [[RESIZE_I]], 8
// UNPADDED-NEXT: {{.*}} = icmp eq i40 [[RESIZE_A]], [[UPSCALE_I]]
// PADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i39
// PADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i39
// PADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// PADDED-NEXT: {{.*}} = icmp eq i39 [[RESIZE_A]], [[UPSCALE_I]]
}
void TestComparisonSignage(void) {
short _Accum sa;
unsigned short _Accum usa;
int i;
unsigned int ui;
// Signed vs unsigned fixed point comparison
sa == usa;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i16, ptr %usa, align 2
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i17
// UNPADDED-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i17 [[RESIZE_A]], 1
// UNPADDED-NEXT: [[RESIZE_A2:%[a-z0-9]+]] = zext i16 [[A2]] to i17
// UNPADDED-NEXT: {{.*}} = icmp eq i17 [[UPSCALE_A]], [[RESIZE_A2]]
// PADDED-NEXT: {{.*}} = icmp eq i16 [[A]], [[A2]]
// Signed int vs unsigned fixed point
sa == ui;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %ui, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i40
// CHECK-NEXT: [[RESIZE_I:%[a-z0-9]+]] = zext i32 [[I]] to i40
// CHECK-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i40 [[RESIZE_I]], 7
// CHECK-NEXT: {{.*}} = icmp eq i40 [[RESIZE_A]], [[UPSCALE_I]]
// Signed fixed point vs unsigned int
usa == i;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %usa, align 2
// CHECK-NEXT: [[I:%[0-9]+]] = load i32, ptr %i, align 4
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i40
// UNPADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i40
// UNPADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i40 [[RESIZE_I]], 8
// UNPADDED-NEXT: {{.*}} = icmp eq i40 [[RESIZE_A]], [[UPSCALE_I]]
// PADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = zext i16 [[A]] to i39
// PADDED-NEXT: [[RESIZE_I:%[a-z0-9]+]] = sext i32 [[I]] to i39
// PADDED-NEXT: [[UPSCALE_I:%[a-z0-9]+]] = shl i39 [[RESIZE_I]], 7
// PADDED-NEXT: {{.*}} = icmp eq i39 [[RESIZE_A]], [[UPSCALE_I]]
}
void TestSaturationComparisons(void) {
short _Accum sa;
_Accum a;
_Sat short _Accum sat_sa;
_Sat _Accum sat_a;
_Sat unsigned short _Accum sat_usa;
// These are effectively the same as conversions with their non-saturating
// counterparts since when comparing, we convert both operands to a common
// type that should be able to hold both values.
sat_sa == sat_a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sat_sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %sat_a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp eq i32 [[UPSCALE_A]], [[A2]]
sat_sa == a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sat_sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: {{.*}} = icmp eq i32 [[UPSCALE_A]], [[A2]]
sat_sa == sat_usa;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sat_sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i16, ptr %sat_usa, align 2
// UNPADDED-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i17
// UNPADDED-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i17 [[RESIZE_A]], 1
// UNPADDED-NEXT: [[RESIZE_A2:%[a-z0-9]+]] = zext i16 [[A2]] to i17
// UNPADDED-NEXT: {{.*}} = icmp eq i17 [[UPSCALE_A]], [[RESIZE_A2]]
// PADDED-NEXT: {{.*}} = icmp eq i16 [[A]], [[A2]]
}
void StoreBooleanResult(void) {
short _Accum sa;
_Accum a;
int res;
// Check that the result can properly be stored as an int.
res = sa == a;
// CHECK: [[A:%[0-9]+]] = load i16, ptr %sa, align 2
// CHECK-NEXT: [[A2:%[0-9]+]] = load i32, ptr %a, align 4
// CHECK-NEXT: [[RESIZE_A:%[a-z0-9]+]] = sext i16 [[A]] to i32
// CHECK-NEXT: [[UPSCALE_A:%[a-z0-9]+]] = shl i32 [[RESIZE_A]], 8
// CHECK-NEXT: [[RES:%[0-9]+]] = icmp eq i32 [[UPSCALE_A]], [[A2]]
// CHECK-NEXT: %conv = zext i1 [[RES]] to i32
// CHECK-NEXT: store i32 %conv, ptr %res, align 4
}
Reference in New Issue View Git Blame Copy Permalink